Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- data/batch_v5/pair_00019/meta.json +237 -0
- data/batch_v5/pair_00026/meta.json +170 -0
- data/batch_v5/pair_01040/meta.json +237 -0
- data/batch_v5/pair_01063/meta.json +304 -0
- data/batch_v5/pair_01074/meta.json +170 -0
- data/batch_v5/pair_01082/meta.json +237 -0
- data/batch_v5/pair_01086/meta.json +170 -0
- data/batch_v5/pair_01090/meta.json +170 -0
- data/batch_v5/pair_01103/meta.json +170 -0
- data/batch_v5/pair_01122/meta.json +170 -0
- data/batch_v5/pair_01126/meta.json +304 -0
- data/batch_v5/pair_01142/meta.json +170 -0
- data/batch_v5/pair_01144/meta.json +237 -0
- data/batch_v5/pair_01148/meta.json +237 -0
- data/batch_v5/pair_01151/meta.json +170 -0
- data/batch_v5/pair_01168/meta.json +170 -0
- data/batch_v5/pair_01172/meta.json +170 -0
- data/batch_v5/pair_01174/meta.json +237 -0
- data/batch_v5/pair_01179/meta.json +170 -0
- data/batch_v5/pair_01195/meta.json +237 -0
- data/batch_v5/pair_01199/meta.json +237 -0
- data/batch_v5/pair_02009/meta.json +170 -0
- data/batch_v5/pair_02013/meta.json +170 -0
- data/batch_v5/pair_02014/meta.json +237 -0
- data/batch_v5/pair_02020/meta.json +237 -0
- data/batch_v5/pair_02021/meta.json +237 -0
- data/batch_v5/pair_02032/meta.json +170 -0
- data/batch_v5/pair_02044/meta.json +170 -0
- data/batch_v5/pair_02046/meta.json +237 -0
- data/batch_v5/pair_02048/meta.json +237 -0
- data/batch_v5/pair_02050/meta.json +170 -0
- data/batch_v5/pair_02051/meta.json +170 -0
- data/batch_v5/pair_02055/meta.json +304 -0
- data/batch_v5/pair_02056/meta.json +170 -0
- data/batch_v5/pair_02062/meta.json +170 -0
- data/batch_v5/pair_02073/meta.json +170 -0
- data/batch_v5/pair_02077/meta.json +170 -0
- data/batch_v5/pair_02088/meta.json +170 -0
- data/batch_v5/pair_02089/meta.json +237 -0
- data/batch_v5/pair_02092/meta.json +170 -0
- data/batch_v5/pair_02104/meta.json +170 -0
- data/batch_v5/pair_02116/meta.json +170 -0
- data/batch_v5/pair_02131/meta.json +304 -0
- data/batch_v5/pair_02139/meta.json +170 -0
- data/batch_v5/pair_02141/meta.json +304 -0
- data/batch_v5/pair_02144/meta.json +237 -0
- data/batch_v5/pair_02149/meta.json +304 -0
- data/batch_v5/pair_02152/meta.json +237 -0
- data/batch_v5/pair_02153/meta.json +237 -0
- data/batch_v5/pair_02177/meta.json +237 -0
data/batch_v5/pair_00019/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 19,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "b62fcbb9-2b80-4d9e-ab5c-a8055ce5532e",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "9bbf3f4c-3de9-4de4-9ad6-7460413fdc88#365",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
5.570888519287109,
|
| 13 |
+
1.4460450410842896,
|
| 14 |
+
0.4067216217517853
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
4.4247355461120605,
|
| 19 |
+
1.6736892461776733,
|
| 20 |
+
0.9572813212871552
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.7745184093583793,
|
| 41 |
+
0.2551751550668659,
|
| 42 |
+
-0.5787977831691883,
|
| 43 |
+
3.711406910184961
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.6325513683211552,
|
| 47 |
+
-0.3124455421457934,
|
| 48 |
+
0.7087006064822121,
|
| 49 |
+
3.134987361811649
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.915020996168843,
|
| 54 |
+
0.4034062178129854,
|
| 55 |
+
1.5785906433152133
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
3.711406910184961,
|
| 66 |
+
3.134987361811649,
|
| 67 |
+
1.5785906433152133
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 1.2917447521794232,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.3718599621213565,
|
| 76 |
+
0.07008875249111512,
|
| 77 |
+
-1.6991359376381077
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.3718599621213574,
|
| 81 |
+
-0.0700887524911149,
|
| 82 |
+
-2.74595752996626
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
448,
|
| 87 |
+
367,
|
| 88 |
+
930,
|
| 89 |
+
626
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
57,
|
| 93 |
+
345,
|
| 94 |
+
833,
|
| 95 |
+
866
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 78873,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_00019/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9949485813998468,
|
| 108 |
+
0.04049627906468814,
|
| 109 |
+
-0.09185516725991731,
|
| 110 |
+
4.7936596307232024
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.10038585742241028,
|
| 114 |
+
0.40136844414090744,
|
| 115 |
+
-0.9103988420892651,
|
| 116 |
+
-0.46353682931180495
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.9150209961688431,
|
| 121 |
+
0.4034062178129854,
|
| 122 |
+
1.5785906433152133
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
4.7936596307232024,
|
| 133 |
+
-0.46353682931180495,
|
| 134 |
+
1.5785906433152133
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.2917447521794232,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.5816077667216373,
|
| 143 |
+
0.2743639772413897,
|
| 144 |
+
-2.162480604601726
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.5816077667216373,
|
| 148 |
+
-0.2743639772413897,
|
| 149 |
+
-2.282612863002641
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
93,
|
| 154 |
+
308,
|
| 155 |
+
394,
|
| 156 |
+
535
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
219,
|
| 160 |
+
472,
|
| 161 |
+
1023,
|
| 162 |
+
931
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 42053,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_00019/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.1003858574224103,
|
| 175 |
+
-0.4013684441409075,
|
| 176 |
+
0.9103988420892651,
|
| 177 |
+
7.021216005642371
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.9949485813998468,
|
| 181 |
+
0.040496279064688154,
|
| 182 |
+
-0.09185516725991733,
|
| 183 |
+
1.355714741654599
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
-0.0,
|
| 187 |
+
0.9150209961688431,
|
| 188 |
+
0.40340621781298547,
|
| 189 |
+
1.5785906433152133
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
7.021216005642371,
|
| 200 |
+
1.355714741654599,
|
| 201 |
+
1.5785906433152133
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 12,
|
| 205 |
+
"dist": 1.2917447521794232,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.05571836498606775,
|
| 210 |
+
0.4865110317834689,
|
| 211 |
+
-2.643680448852443
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.05571836498606797,
|
| 215 |
+
-0.48651103178346955,
|
| 216 |
+
-1.8014130187519228
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
363,
|
| 221 |
+
292,
|
| 222 |
+
703,
|
| 223 |
+
412
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
0,
|
| 227 |
+
425,
|
| 228 |
+
812,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 33778,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_00019/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_00026/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 26,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "3f6d609d-29ca-44c8-a5e0-005163494d5c",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "06543b99-4fe3-4be8-be81-f62a83bbee97#827",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
0.02369023859500885,
|
| 13 |
+
0.006527334451675415,
|
| 14 |
+
0.3763450086116791
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.2514688968658447,
|
| 19 |
+
0.19979913625866175,
|
| 20 |
+
1.2676900625228882
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.6898316208906614,
|
| 41 |
+
0.3935750525475555,
|
| 42 |
+
-0.60764382069725,
|
| 43 |
+
-2.3238558175553954
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.7239698438604766,
|
| 47 |
+
-0.37501633354404057,
|
| 48 |
+
0.5789908589570496,
|
| 49 |
+
1.732497612164924
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8393220047081893,
|
| 54 |
+
0.543634594569391,
|
| 55 |
+
2.3518560807741777
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-2.3238558175553954,
|
| 66 |
+
1.732497612164924,
|
| 67 |
+
2.3518560807741777
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 1.5677629971570852,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.3698610685658289,
|
| 76 |
+
0.08688730564943892,
|
| 77 |
+
-2.128437846618636
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.36986106856582923,
|
| 81 |
+
-0.08688730564943875,
|
| 82 |
+
-3.499749029231927
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
614,
|
| 87 |
+
226,
|
| 88 |
+
731,
|
| 89 |
+
731
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
210,
|
| 93 |
+
359,
|
| 94 |
+
638,
|
| 95 |
+
746
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 30743,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_00026/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 225,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.024139368959614885,
|
| 108 |
+
-0.5434761810669355,
|
| 109 |
+
0.8390774287746818,
|
| 110 |
+
1.7473529570906319
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.9997086029770034,
|
| 114 |
+
-0.01312299605752118,
|
| 115 |
+
0.020260703547574605,
|
| 116 |
+
0.16017874825614775
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8393220047081895,
|
| 121 |
+
0.543634594569391,
|
| 122 |
+
2.3518560807741777
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
1.7473529570906319,
|
| 133 |
+
0.16017874825614775,
|
| 134 |
+
2.3518560807741777
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 12,
|
| 138 |
+
"dist": 1.5677629971570852,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.11199850991621178,
|
| 143 |
+
0.7193039148176108,
|
| 144 |
+
-3.104831147413316
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.11199850991621182,
|
| 148 |
+
-0.719303914817611,
|
| 149 |
+
-2.523355728437246
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
0,
|
| 154 |
+
0,
|
| 155 |
+
0,
|
| 156 |
+
0
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
0,
|
| 160 |
+
0,
|
| 161 |
+
0,
|
| 162 |
+
0
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 0,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_00026/view_01_right/rgb.png",
|
| 166 |
+
"ok": false
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": false
|
| 170 |
+
}
|
data/batch_v5/pair_01040/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1040,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "ec064a37-13a7-49ef-89f6-7ccedbc9123a",
|
| 6 |
+
"target_category": "chair",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "4000ed3d-3e7c-41a1-a869-107813bc55a7#558",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.36803263425827026,
|
| 13 |
+
2.2855567932128906,
|
| 14 |
+
0.3659999966621399
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.9470962435007095,
|
| 19 |
+
0.49675149098038673,
|
| 20 |
+
1.2470000088214874
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.5864438802749503,
|
| 41 |
+
0.2742651370864497,
|
| 42 |
+
-0.7621431688777448,
|
| 43 |
+
-2.9491759349829363
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.8099898612254722,
|
| 47 |
+
0.19857175863136678,
|
| 48 |
+
-0.5518022121974381,
|
| 49 |
+
-0.2680043266579415
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.9409292700585932,
|
| 54 |
+
0.3386031729724381,
|
| 55 |
+
1.824611763742472
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-2.9491759349829363,
|
| 66 |
+
-0.2680043266579415,
|
| 67 |
+
1.824611763742472
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 2,
|
| 71 |
+
"dist": 2.076367042280524,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.5546629242922705,
|
| 76 |
+
0.15746776173931665,
|
| 77 |
+
-2.1434464853381563
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.5546629242922705,
|
| 81 |
+
-0.1574677617393162,
|
| 82 |
+
-3.870151981936287
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
621,
|
| 87 |
+
226,
|
| 88 |
+
909,
|
| 89 |
+
703
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
218,
|
| 93 |
+
446,
|
| 94 |
+
261,
|
| 95 |
+
520
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 42245,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01040/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.15807087903711292,
|
| 108 |
+
-0.3343461753572644,
|
| 109 |
+
0.9290996890670041,
|
| 110 |
+
2.1360517941797585
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.9874277680926511,
|
| 114 |
+
0.05352330119650888,
|
| 115 |
+
-0.14873351682991084,
|
| 116 |
+
0.943942317676294
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.9409292700585932,
|
| 121 |
+
0.3386031729724381,
|
| 122 |
+
1.824611763742472
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
2.1360517941797585,
|
| 133 |
+
0.943942317676294,
|
| 134 |
+
1.824611763742472
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 2.076367042280524,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.9289245604335485,
|
| 143 |
+
0.46341181821409383,
|
| 144 |
+
-2.9936207917703332
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.9289245604335488,
|
| 148 |
+
-0.4634118182140936,
|
| 149 |
+
-3.0199776755041094
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
260,
|
| 154 |
+
217,
|
| 155 |
+
327,
|
| 156 |
+
536
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
567,
|
| 160 |
+
507,
|
| 161 |
+
1023,
|
| 162 |
+
811
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 7982,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01040/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.9874277680926511,
|
| 175 |
+
-0.0535233011965089,
|
| 176 |
+
0.1487335168299109,
|
| 177 |
+
-0.21035261445914505
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.15807087903711298,
|
| 181 |
+
-0.3343461753572644,
|
| 182 |
+
0.9290996890670041,
|
| 183 |
+
4.184770375155887
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.9409292700585932,
|
| 188 |
+
0.3386031729724381,
|
| 189 |
+
1.824611763742472
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-0.21035261445914505,
|
| 200 |
+
4.184770375155887,
|
| 201 |
+
1.824611763742472
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 12,
|
| 205 |
+
"dist": 2.076367042280524,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.14451273035389822,
|
| 210 |
+
0.7290161527961798,
|
| 211 |
+
-3.7316968424725028
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.144512730353898,
|
| 215 |
+
-0.7290161527961807,
|
| 216 |
+
-2.2819016248019373
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
481,
|
| 221 |
+
212,
|
| 222 |
+
622,
|
| 223 |
+
471
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
312,
|
| 227 |
+
554,
|
| 228 |
+
659,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 13359,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01040/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_01063/meta.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1063,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "45078a8f-0573-472a-8523-38017a834801",
|
| 6 |
+
"target_category": "chair",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "bef459c6-112e-4678-b361-a345e3da9c0d#364",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.317015677690506,
|
| 13 |
+
-1.7106610536575317,
|
| 14 |
+
0.36833590269088745
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
1.4259369522333145,
|
| 19 |
+
-2.3371169567108154,
|
| 20 |
+
1.2517451047897339
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.22086008321242712,
|
| 41 |
+
-0.5417904369128126,
|
| 42 |
+
0.8109771551117969,
|
| 43 |
+
2.8710989233124384
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9753055027238389,
|
| 47 |
+
0.12268963996006814,
|
| 48 |
+
-0.1836475662868122,
|
| 49 |
+
-2.5484968569795035
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.8315108987357248,
|
| 54 |
+
0.5555084385351022,
|
| 55 |
+
2.3969065563998133
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
2.8710989233124384,
|
| 66 |
+
-2.5484968569795035,
|
| 67 |
+
2.3969065563998133
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 7,
|
| 71 |
+
"dist": 2.0520094266307813,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.11301861329070295,
|
| 76 |
+
-0.14330516824630352,
|
| 77 |
+
-1.8469595980823046
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.11301861329070251,
|
| 81 |
+
0.14330516824630424,
|
| 82 |
+
-3.8662427318197627
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
293,
|
| 87 |
+
416,
|
| 88 |
+
648,
|
| 89 |
+
879
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
0,
|
| 93 |
+
0,
|
| 94 |
+
0,
|
| 95 |
+
0
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 58612,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01063/view_00_front/rgb.png",
|
| 99 |
+
"ok": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9753055027238386,
|
| 108 |
+
-0.12268963996006825,
|
| 109 |
+
0.18364756628681236,
|
| 110 |
+
1.0790684890667346
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.22086008321242728,
|
| 114 |
+
-0.5417904369128126,
|
| 115 |
+
0.8109771551117969,
|
| 116 |
+
0.29274928085686014
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8315108987357247,
|
| 121 |
+
0.5555084385351023,
|
| 122 |
+
2.3969065563998133
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
1.0790684890667346,
|
| 133 |
+
0.29274928085686014,
|
| 134 |
+
2.3969065563998133
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 2.0520094266307813,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.9191351969144766,
|
| 143 |
+
0.4300649831888317,
|
| 144 |
+
-2.7052067404395155
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.9191351969144764,
|
| 148 |
+
-0.4300649831888308,
|
| 149 |
+
-3.0079955894625514
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
28,
|
| 154 |
+
206,
|
| 155 |
+
257,
|
| 156 |
+
572
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
464,
|
| 160 |
+
436,
|
| 161 |
+
1023,
|
| 162 |
+
760
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 15330,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01063/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.22086008321242728,
|
| 175 |
+
0.5417904369128126,
|
| 176 |
+
-0.8109771551117969,
|
| 177 |
+
-1.7621776487696295
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.9753055027238386,
|
| 181 |
+
-0.12268963996006825,
|
| 182 |
+
0.18364756628681236,
|
| 183 |
+
-1.4992811533888433
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.8315108987357247,
|
| 188 |
+
0.5555084385351023,
|
| 189 |
+
2.3969065563998133
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-1.7621776487696295,
|
| 200 |
+
-1.4992811533888433,
|
| 201 |
+
2.3969065563998133
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 12,
|
| 205 |
+
"dist": 2.0520094266307813,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.11301861329070295,
|
| 210 |
+
0.877869547834925,
|
| 211 |
+
-3.375501465374291
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.11301861329070229,
|
| 215 |
+
-0.8778695478349253,
|
| 216 |
+
-2.3377008645277746
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
0,
|
| 221 |
+
0,
|
| 222 |
+
0,
|
| 223 |
+
0
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
246,
|
| 227 |
+
467,
|
| 228 |
+
812,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 0,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01063/view_02_back/rgb.png",
|
| 233 |
+
"ok": false
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"view_idx": 3,
|
| 237 |
+
"view_label": "left",
|
| 238 |
+
"azimuth_offset_deg": 270,
|
| 239 |
+
"cam2world": [
|
| 240 |
+
[
|
| 241 |
+
0.9753055027238389,
|
| 242 |
+
0.12268963996006807,
|
| 243 |
+
-0.18364756628681206,
|
| 244 |
+
0.02985278547607484
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
-0.22086008321242695,
|
| 248 |
+
0.5417904369128127,
|
| 249 |
+
-0.8109771551117969,
|
| 250 |
+
-4.340527291225207
|
| 251 |
+
],
|
| 252 |
+
[
|
| 253 |
+
0.0,
|
| 254 |
+
0.8315108987357247,
|
| 255 |
+
0.5555084385351023,
|
| 256 |
+
2.3969065563998133
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
0.0,
|
| 260 |
+
0.0,
|
| 261 |
+
0.0,
|
| 262 |
+
1.0
|
| 263 |
+
]
|
| 264 |
+
],
|
| 265 |
+
"cam_pos_world": [
|
| 266 |
+
0.02985278547607484,
|
| 267 |
+
-4.340527291225207,
|
| 268 |
+
2.3969065563998133
|
| 269 |
+
],
|
| 270 |
+
"gt": {
|
| 271 |
+
"clock": 2,
|
| 272 |
+
"dist": 2.0520094266307813,
|
| 273 |
+
"lr": "right",
|
| 274 |
+
"fb": "in front of",
|
| 275 |
+
"target_cam_xyz": [
|
| 276 |
+
0.919135196914476,
|
| 277 |
+
0.3044993963997897,
|
| 278 |
+
-2.51725432301708
|
| 279 |
+
],
|
| 280 |
+
"anchor_cam_xyz": [
|
| 281 |
+
-0.9191351969144764,
|
| 282 |
+
-0.30449939639978957,
|
| 283 |
+
-3.195948006884986
|
| 284 |
+
]
|
| 285 |
+
},
|
| 286 |
+
"target_bbox": [
|
| 287 |
+
763,
|
| 288 |
+
198,
|
| 289 |
+
1023,
|
| 290 |
+
569
|
| 291 |
+
],
|
| 292 |
+
"anchor_bbox": [
|
| 293 |
+
0,
|
| 294 |
+
408,
|
| 295 |
+
636,
|
| 296 |
+
787
|
| 297 |
+
],
|
| 298 |
+
"target_pixels": 24250,
|
| 299 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01063/view_03_left/rgb.png",
|
| 300 |
+
"ok": true
|
| 301 |
+
}
|
| 302 |
+
],
|
| 303 |
+
"all_views_ok": false
|
| 304 |
+
}
|
data/batch_v5/pair_01074/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1074,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "697a1396-5e87-4761-b8b0-844b64c87a4b",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "2383a24b-483b-4011-87fb-8e2c89202f78#290",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.6634702682495117,
|
| 13 |
+
5.520051956176758,
|
| 14 |
+
0.16750000417232513
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-2.7646602988243103,
|
| 19 |
+
5.282294273376465,
|
| 20 |
+
0.720798909664154
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.7097293159309067,
|
| 41 |
+
0.4197547806187432,
|
| 42 |
+
-0.5657651652902976,
|
| 43 |
+
-3.588602344337077
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.7044744836459637,
|
| 47 |
+
0.4228858251408087,
|
| 48 |
+
-0.5699853338347665,
|
| 49 |
+
4.016383075491602
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.803102423755954,
|
| 54 |
+
0.5958409997283771,
|
| 55 |
+
1.891756320537422
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-3.588602344337077,
|
| 66 |
+
4.016383075491602,
|
| 67 |
+
1.891756320537422
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.2551047278957825,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.30702631314309325,
|
| 76 |
+
-0.05920922075801949,
|
| 77 |
+
-1.8854129586348098
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.3070263131430959,
|
| 81 |
+
0.05920922075801638,
|
| 82 |
+
-2.973624483498563
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
65,
|
| 87 |
+
308,
|
| 88 |
+
592,
|
| 89 |
+
800
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
482,
|
| 93 |
+
349,
|
| 94 |
+
864,
|
| 95 |
+
709
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 125515,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01074/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 270,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.7044744836459638,
|
| 108 |
+
0.4228858251408087,
|
| 109 |
+
-0.5699853338347664,
|
| 110 |
+
-3.59885532282192
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.7097293159309066,
|
| 114 |
+
-0.4197547806187434,
|
| 115 |
+
0.5657651652902977,
|
| 116 |
+
6.775710175576777
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.803102423755954,
|
| 121 |
+
0.5958409997283772,
|
| 122 |
+
1.891756320537422
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-3.59885532282192,
|
| 133 |
+
6.775710175576777,
|
| 134 |
+
1.891756320537422
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 3,
|
| 138 |
+
"dist": 1.2551047278957825,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.47225193787821684,
|
| 143 |
+
0.03923898066490361,
|
| 144 |
+
-2.018106058326177
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.47225193787821684,
|
| 148 |
+
-0.03923898066490272,
|
| 149 |
+
-2.8409313838071926
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
535,
|
| 154 |
+
270,
|
| 155 |
+
1003,
|
| 156 |
+
753
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
85,
|
| 160 |
+
364,
|
| 161 |
+
567,
|
| 162 |
+
758
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 109813,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01074/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01082/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1082,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "846bef72-20b1-4910-918d-cf16981a1c70",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "1d127f82-0a20-4417-b879-08d73f208a0a#663",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.5907164812088013,
|
| 13 |
+
2.0854697227478027,
|
| 14 |
+
0.589899480342865
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.2591773346066475,
|
| 19 |
+
1.1623936295509338,
|
| 20 |
+
1.1062918901443481
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.440534195285514,
|
| 41 |
+
-0.7131154019711068,
|
| 42 |
+
0.5453403031646674,
|
| 43 |
+
1.286564167957617
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.8977358312912238,
|
| 47 |
+
0.3499378200168298,
|
| 48 |
+
-0.26760773407680916,
|
| 49 |
+
0.5387056907165824
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.6074618881818477,
|
| 54 |
+
0.7943488241361879,
|
| 55 |
+
4.069407611912897
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
1.286564167957617,
|
| 66 |
+
0.5387056907165824,
|
| 67 |
+
4.069407611912897
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 6,
|
| 71 |
+
"dist": 1.7005078928561812,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.12104497871580322,
|
| 76 |
+
-0.4794358006158197,
|
| 77 |
+
-3.3636063450713993
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.12104497871580278,
|
| 81 |
+
0.47943580061582125,
|
| 82 |
+
-4.746966312154589
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
413,
|
| 87 |
+
513,
|
| 88 |
+
556,
|
| 89 |
+
781
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
282,
|
| 93 |
+
274,
|
| 94 |
+
797,
|
| 95 |
+
619
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 8018,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01082/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.8977358312912237,
|
| 108 |
+
-0.34993782001683,
|
| 109 |
+
0.2676077340768092,
|
| 110 |
+
0.16027907752506176
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.4405341952855142,
|
| 114 |
+
-0.7131154019711067,
|
| 115 |
+
0.5453403031646673,
|
| 116 |
+
3.835442752014709
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.6074618881818475,
|
| 121 |
+
0.7943488241361879,
|
| 122 |
+
4.069407611912897
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
0.16027907752506176,
|
| 133 |
+
3.835442752014709,
|
| 134 |
+
4.069407611912897
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.7005078928561812,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.8010084932877349,
|
| 143 |
+
0.2529962906608795,
|
| 144 |
+
-3.9237186881792976
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.801008493287735,
|
| 148 |
+
-0.25299629066088003,
|
| 149 |
+
-4.186853969046692
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
206,
|
| 154 |
+
392,
|
| 155 |
+
447,
|
| 156 |
+
519
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
466,
|
| 160 |
+
340,
|
| 161 |
+
951,
|
| 162 |
+
900
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 16340,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01082/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.4405341952855143,
|
| 175 |
+
0.7131154019711067,
|
| 176 |
+
-0.5453403031646673,
|
| 177 |
+
-3.1364579837730653
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.8977358312912237,
|
| 181 |
+
-0.34993782001683005,
|
| 182 |
+
0.26760773407680927,
|
| 183 |
+
2.7091576615821547
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.6074618881818477,
|
| 188 |
+
0.7943488241361879,
|
| 189 |
+
4.069407611912897
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-3.1364579837730653,
|
| 200 |
+
2.7091576615821547,
|
| 201 |
+
4.069407611912897
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 12,
|
| 205 |
+
"dist": 1.7005078928561812,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.12104497871580344,
|
| 210 |
+
0.7931245089166035,
|
| 211 |
+
-4.336770608635928
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.12104497871580255,
|
| 215 |
+
-0.7931245089166035,
|
| 216 |
+
-3.77380204859006
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
482,
|
| 221 |
+
264,
|
| 222 |
+
599,
|
| 223 |
+
443
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
130,
|
| 227 |
+
506,
|
| 228 |
+
722,
|
| 229 |
+
787
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 7174,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01082/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_01086/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1086,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "288ac6f4-47ef-418d-87d0-6cc1365a98f4",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "31d93b50-3d5d-4962-ab4e-d92c0249ec74#196",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
3.960742235183716,
|
| 13 |
+
3.448499917984009,
|
| 14 |
+
0.2741914987564087
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
2.7121384143829346,
|
| 19 |
+
3.45128732919693,
|
| 20 |
+
1.0633830726146698
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.2977081271169954,
|
| 41 |
+
-0.7980652576487726,
|
| 42 |
+
0.5238909386336903,
|
| 43 |
+
5.207026424970524
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9546569389306773,
|
| 47 |
+
-0.24887528020053618,
|
| 48 |
+
0.16337448961393478,
|
| 49 |
+
4.0332326868581525
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5487740331312176,
|
| 54 |
+
0.8359707294881186,
|
| 55 |
+
3.6536742371989726
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
5.207026424970524,
|
| 66 |
+
4.0332326868581525,
|
| 67 |
+
3.6536742371989726
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 12,
|
| 71 |
+
"dist": 1.4771061611233156,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.18719026322889665,
|
| 76 |
+
0.7144307275506692,
|
| 77 |
+
-3.567531841887941
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.18719026322889665,
|
| 81 |
+
-0.7144307275506696,
|
| 82 |
+
-3.57359606181543
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
382,
|
| 87 |
+
135,
|
| 88 |
+
731,
|
| 89 |
+
521
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
254,
|
| 93 |
+
568,
|
| 94 |
+
670,
|
| 95 |
+
848
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 74265,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01086/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9546569389306773,
|
| 108 |
+
0.24887528020053618,
|
| 109 |
+
-0.16337448961393478,
|
| 110 |
+
2.753101261515642
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.2977081271169954,
|
| 114 |
+
-0.7980652576487726,
|
| 115 |
+
0.5238909386336903,
|
| 116 |
+
5.320479723777668
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.5487740331312176,
|
| 121 |
+
0.8359707294881186,
|
| 122 |
+
3.6536742371989726
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
2.753101261515642,
|
| 133 |
+
5.320479723777668,
|
| 134 |
+
3.6536742371989726
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 3,
|
| 138 |
+
"dist": 1.4771061611233156,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.5955792332655596,
|
| 143 |
+
0.060058340545151134,
|
| 144 |
+
-3.137968268284587
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.5955792332655587,
|
| 148 |
+
-0.0600583405451518,
|
| 149 |
+
-4.003159635418786
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
494,
|
| 154 |
+
259,
|
| 155 |
+
892,
|
| 156 |
+
696
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
233,
|
| 160 |
+
384,
|
| 161 |
+
501,
|
| 162 |
+
725
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 91266,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01086/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01090/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1090,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "1cef5e59-b64f-4de6-a54d-a7b38832bfa4",
|
| 6 |
+
"target_category": "chair",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "e4adc6e9-5286-44d3-9aff-951d46e5537e#246",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-2.6551272869110107,
|
| 13 |
+
6.066786766052246,
|
| 14 |
+
0.3650589883327484
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.9799264073371887,
|
| 19 |
+
4.98525857925415,
|
| 20 |
+
1.2451179325580597
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.5926955347949835,
|
| 41 |
+
-0.5113370129173594,
|
| 42 |
+
0.6222913001600141,
|
| 43 |
+
-1.0825868248782244
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.8054265969249392,
|
| 47 |
+
0.37628154507016826,
|
| 48 |
+
-0.4579303394682629,
|
| 49 |
+
4.617257752647756
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.7726232316338665,
|
| 54 |
+
0.6348648217846385,
|
| 55 |
+
2.0649806956996084
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-1.0825868248782244,
|
| 66 |
+
4.617257752647756,
|
| 67 |
+
2.0649806956996084
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.5492266431762038,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.2354515102790704,
|
| 76 |
+
-0.03613015626506355,
|
| 77 |
+
-1.2474273859156215
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.23545151027906996,
|
| 81 |
+
0.036130156265063995,
|
| 82 |
+
-2.721582053645326
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
123,
|
| 87 |
+
114,
|
| 88 |
+
630,
|
| 89 |
+
1000
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
376,
|
| 93 |
+
277,
|
| 94 |
+
894,
|
| 95 |
+
791
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 113143,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01090/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 270,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.8054265969249392,
|
| 108 |
+
0.37628154507016826,
|
| 109 |
+
-0.4579303394682629,
|
| 110 |
+
-3.226291767129542
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.5926955347949835,
|
| 114 |
+
0.5113370129173594,
|
| 115 |
+
-0.6222913001600141,
|
| 116 |
+
4.291082650407323
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7726232316338665,
|
| 121 |
+
0.6348648217846385,
|
| 122 |
+
2.0649806956996084
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-3.226291767129542,
|
| 133 |
+
4.291082650407323,
|
| 134 |
+
2.0649806956996084
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 2,
|
| 138 |
+
"dist": 1.5492266431762038,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.592420836873008,
|
| 143 |
+
0.1904971116455778,
|
| 144 |
+
-1.523230180622794
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.5924208368730071,
|
| 148 |
+
-0.19049711164557914,
|
| 149 |
+
-2.445779258938153
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
590,
|
| 154 |
+
81,
|
| 155 |
+
1023,
|
| 156 |
+
786
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
0,
|
| 160 |
+
342,
|
| 161 |
+
581,
|
| 162 |
+
879
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 70832,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01090/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01103/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1103,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "079431be-2e6d-4ff0-8c0e-7b80e764bf59",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "9dd6c801-a614-4418-ab03-d521a7e0cf33#418",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.6030000448226929,
|
| 13 |
+
-2.909146785736084,
|
| 14 |
+
0.3876135051250458
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-2.565123200416565,
|
| 19 |
+
-1.3543433547019958,
|
| 20 |
+
1.1426431238651276
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.3773653819412557,
|
| 41 |
+
0.44119395455236654,
|
| 42 |
+
-0.8142132785571448,
|
| 43 |
+
-4.466156751616035
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9260644515973661,
|
| 47 |
+
-0.17978373414792714,
|
| 48 |
+
0.3317867393725934,
|
| 49 |
+
-1.1610564355094488
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8792188029166983,
|
| 54 |
+
0.4764181950741682,
|
| 55 |
+
2.158956555496668
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-4.466156751616035,
|
| 66 |
+
-1.1610564355094488,
|
| 67 |
+
2.158956555496668
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.9781719846515053,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.5383881073085388,
|
| 76 |
+
-0.02008752446243728,
|
| 77 |
+
-2.0961670077790533
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.5383881073085393,
|
| 81 |
+
0.020087524462436557,
|
| 82 |
+
-3.755113465606694
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
107,
|
| 87 |
+
314,
|
| 88 |
+
421,
|
| 89 |
+
803
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
452,
|
| 93 |
+
343,
|
| 94 |
+
771,
|
| 95 |
+
636
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 115098,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01103/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9260644515973661,
|
| 108 |
+
0.1797837341479272,
|
| 109 |
+
-0.3317867393725935,
|
| 110 |
+
-3.0547502573292205
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.37736538194125585,
|
| 114 |
+
0.4411939545523665,
|
| 115 |
+
-0.8142132785571446,
|
| 116 |
+
-4.513840199215446
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8792188029166983,
|
| 121 |
+
0.47641819507416816,
|
| 122 |
+
2.158956555496668
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-3.0547502573292205,
|
| 133 |
+
-4.513840199215446,
|
| 134 |
+
2.158956555496668
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.9781719846515053,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.7388585215249599,
|
| 143 |
+
0.5884160091109849,
|
| 144 |
+
-3.2191462598114313
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.7388585215249599,
|
| 148 |
+
-0.5884160091109845,
|
| 149 |
+
-2.632134213574317
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
140,
|
| 154 |
+
231,
|
| 155 |
+
451,
|
| 156 |
+
463
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
356,
|
| 160 |
+
482,
|
| 161 |
+
1023,
|
| 162 |
+
1002
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 62235,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01103/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01122/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1122,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "00063df5-b7d7-42af-a11c-ac8a690272fd",
|
| 6 |
+
"target_category": "lighting",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "03b0d05c-a430-4853-84f0-f8aeb802e6c5#366",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-3.7698731422424316,
|
| 13 |
+
5.648894309997559,
|
| 14 |
+
0.4612582325935364
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-4.417694926261902,
|
| 19 |
+
6.526928663253784,
|
| 20 |
+
1.4375150799751282
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.22043457962164728,
|
| 41 |
+
0.6591684649382034,
|
| 42 |
+
-0.7189614252086408,
|
| 43 |
+
-7.212216424958974
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9754017613819589,
|
| 47 |
+
-0.14896787069835912,
|
| 48 |
+
0.16248069852314548,
|
| 49 |
+
6.7926573260734635
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.737092604989773,
|
| 54 |
+
0.6757917517026901,
|
| 55 |
+
3.880574358420919
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-7.212216424958974,
|
| 66 |
+
6.7926573260734635,
|
| 67 |
+
3.880574358420919
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.4641362031613356,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.3568169660449563,
|
| 76 |
+
0.08088455192268329,
|
| 77 |
+
-3.7033282475263887
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.35681696604495716,
|
| 81 |
+
-0.08088455192268373,
|
| 82 |
+
-4.971497080694373
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
335,
|
| 87 |
+
422,
|
| 88 |
+
568,
|
| 89 |
+
637
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
373,
|
| 93 |
+
427,
|
| 94 |
+
808,
|
| 95 |
+
687
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 14796,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01122/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 180,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.22043457962164725,
|
| 108 |
+
-0.6591684649382034,
|
| 109 |
+
0.7189614252086409,
|
| 110 |
+
-0.9753516435453586
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.9754017613819589,
|
| 114 |
+
0.14896787069835912,
|
| 115 |
+
-0.16248069852314548,
|
| 116 |
+
5.383165647177879
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.737092604989773,
|
| 121 |
+
0.6757917517026901,
|
| 122 |
+
3.880574358420919
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-0.9753516435453586,
|
| 133 |
+
5.383165647177879,
|
| 134 |
+
3.880574358420919
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.4641362031613356,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.3568169660449563,
|
| 143 |
+
0.638707150852917,
|
| 144 |
+
-4.311750755690622
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.35681696604495716,
|
| 148 |
+
-0.6387071508529165,
|
| 149 |
+
-4.363074572530142
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
466,
|
| 154 |
+
263,
|
| 155 |
+
651,
|
| 156 |
+
440
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
200,
|
| 160 |
+
494,
|
| 161 |
+
690,
|
| 162 |
+
834
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 9395,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01122/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01126/meta.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1126,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "4c1e3615-3f33-43e7-b619-0032a2550e74",
|
| 6 |
+
"target_category": "lighting",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "3332e155-0105-4d97-937a-b7a64daedb40#810",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
3.6003713607788086,
|
| 13 |
+
-3.3857831954956055,
|
| 14 |
+
0.30711498856544495
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
3.066452145576477,
|
| 19 |
+
-3.86235648393631,
|
| 20 |
+
1.1107538044452667
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.583837730657114,
|
| 41 |
+
-0.4768217569780652,
|
| 42 |
+
0.6570955153807566,
|
| 43 |
+
5.172728277866601
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.8118703740506554,
|
| 47 |
+
0.3428952963674001,
|
| 48 |
+
-0.4725349843852427,
|
| 49 |
+
-4.946771615834135
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.809360134798758,
|
| 54 |
+
0.587312669877414,
|
| 55 |
+
2.352917460731203
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
5.172728277866601,
|
| 66 |
+
-4.946771615834135,
|
| 67 |
+
2.352917460731203
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 11,
|
| 71 |
+
"dist": 1.0761167102160354,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.3493189584534312,
|
| 76 |
+
0.3708013898232352,
|
| 77 |
+
-2.6259871414978084
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.34931895845343097,
|
| 81 |
+
-0.3708013898232356,
|
| 82 |
+
-2.972336029595997
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
200,
|
| 87 |
+
209,
|
| 88 |
+
562,
|
| 89 |
+
567
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
479,
|
| 93 |
+
472,
|
| 94 |
+
769,
|
| 95 |
+
734
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 95040,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01126/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.8118703740506554,
|
| 108 |
+
-0.3428952963674001,
|
| 109 |
+
0.4725349843852427,
|
| 110 |
+
4.65611352929582
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.583837730657114,
|
| 114 |
+
-0.4768217569780652,
|
| 115 |
+
0.6570955153807565,
|
| 116 |
+
-1.7847533150269996
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8093601347987579,
|
| 121 |
+
0.587312669877414,
|
| 122 |
+
2.352917460731203
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
4.65611352929582,
|
| 133 |
+
-1.7847533150269996,
|
| 134 |
+
2.352917460731203
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 12,
|
| 138 |
+
"dist": 1.0761167102160354,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.07761586287206512,
|
| 143 |
+
0.5303760603030854,
|
| 144 |
+
-2.8458927955627833
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.07761586287206512,
|
| 148 |
+
-0.5303760603030854,
|
| 149 |
+
-2.7524303755310235
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
437,
|
| 154 |
+
177,
|
| 155 |
+
625,
|
| 156 |
+
494
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
327,
|
| 160 |
+
517,
|
| 161 |
+
641,
|
| 162 |
+
803
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 50379,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01126/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.583837730657114,
|
| 175 |
+
0.4768217569780652,
|
| 176 |
+
-0.6570955153807565,
|
| 177 |
+
1.4940952284886848
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.8118703740506554,
|
| 181 |
+
-0.3428952963674001,
|
| 182 |
+
0.4725349843852427,
|
| 183 |
+
-2.3013680635977805
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.8093601347987579,
|
| 188 |
+
0.587312669877414,
|
| 189 |
+
2.352917460731203
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
1.4940952284886848,
|
| 200 |
+
-2.3013680635977805,
|
| 201 |
+
2.352917460731203
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 2,
|
| 205 |
+
"dist": 1.0761167102160354,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.3493189584534314,
|
| 210 |
+
0.279631830526772,
|
| 211 |
+
-2.5003487710244965
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.34931895845343075,
|
| 215 |
+
-0.2796318305267711,
|
| 216 |
+
-3.0979744000693112
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
455,
|
| 221 |
+
212,
|
| 222 |
+
824,
|
| 223 |
+
573
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
265,
|
| 227 |
+
449,
|
| 228 |
+
540,
|
| 229 |
+
699
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 97538,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01126/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"view_idx": 3,
|
| 237 |
+
"view_label": "left",
|
| 238 |
+
"azimuth_offset_deg": 270,
|
| 239 |
+
"cam2world": [
|
| 240 |
+
[
|
| 241 |
+
0.8118703740506554,
|
| 242 |
+
0.3428952963674001,
|
| 243 |
+
-0.4725349843852427,
|
| 244 |
+
2.0107099770594656
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
-0.583837730657114,
|
| 248 |
+
0.4768217569780652,
|
| 249 |
+
-0.6570955153807566,
|
| 250 |
+
-5.463386364404916
|
| 251 |
+
],
|
| 252 |
+
[
|
| 253 |
+
0.0,
|
| 254 |
+
0.809360134798758,
|
| 255 |
+
0.587312669877414,
|
| 256 |
+
2.352917460731203
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
0.0,
|
| 260 |
+
0.0,
|
| 261 |
+
0.0,
|
| 262 |
+
1.0
|
| 263 |
+
]
|
| 264 |
+
],
|
| 265 |
+
"cam_pos_world": [
|
| 266 |
+
2.0107099770594656,
|
| 267 |
+
-5.463386364404916,
|
| 268 |
+
2.352917460731203
|
| 269 |
+
],
|
| 270 |
+
"gt": {
|
| 271 |
+
"clock": 11,
|
| 272 |
+
"dist": 1.0761167102160354,
|
| 273 |
+
"lr": "left",
|
| 274 |
+
"fb": "in front of",
|
| 275 |
+
"target_cam_xyz": [
|
| 276 |
+
-0.07761586287206423,
|
| 277 |
+
0.12005716004692095,
|
| 278 |
+
-2.280443116959521
|
| 279 |
+
],
|
| 280 |
+
"anchor_cam_xyz": [
|
| 281 |
+
0.07761586287206601,
|
| 282 |
+
-0.12005716004692187,
|
| 283 |
+
-3.3178800541342843
|
| 284 |
+
]
|
| 285 |
+
},
|
| 286 |
+
"target_bbox": [
|
| 287 |
+
349,
|
| 288 |
+
259,
|
| 289 |
+
590,
|
| 290 |
+
660
|
| 291 |
+
],
|
| 292 |
+
"anchor_bbox": [
|
| 293 |
+
421,
|
| 294 |
+
420,
|
| 295 |
+
662,
|
| 296 |
+
599
|
| 297 |
+
],
|
| 298 |
+
"target_pixels": 84103,
|
| 299 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01126/view_03_left/rgb.png",
|
| 300 |
+
"ok": true
|
| 301 |
+
}
|
| 302 |
+
],
|
| 303 |
+
"all_views_ok": true
|
| 304 |
+
}
|
data/batch_v5/pair_01142/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1142,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "ea0be776-bedd-48cc-b929-e1f79e4e847e",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "5b9cfb19-f47f-4291-8531-45b9c6ebc865#239",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
3.735135793685913,
|
| 13 |
+
3.710242748260498,
|
| 14 |
+
0.4722078740596771
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
3.6293579936027527,
|
| 19 |
+
2.8916547298431396,
|
| 20 |
+
1.4595320522785187
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.07063283336503126,
|
| 41 |
+
0.4687595418265995,
|
| 42 |
+
-0.8804972997104217,
|
| 43 |
+
1.043169636627446
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9975023823785223,
|
| 47 |
+
0.03319271732179425,
|
| 48 |
+
-0.06234773986254621,
|
| 49 |
+
3.1140764995210843
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8827019516593989,
|
| 54 |
+
0.4699332554062205,
|
| 55 |
+
2.374381002403788
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
1.043169636627446,
|
| 66 |
+
3.1140764995210843,
|
| 67 |
+
2.374381002403788
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 2,
|
| 71 |
+
"dist": 1.2868893968723192,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.40453605641541746,
|
| 76 |
+
0.39737873261677015,
|
| 77 |
+
-2.6931823155609727
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.40453605641541834,
|
| 81 |
+
-0.3973787326167706,
|
| 82 |
+
-3.3013329609420383
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
472,
|
| 87 |
+
182,
|
| 88 |
+
794,
|
| 89 |
+
627
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
33,
|
| 93 |
+
459,
|
| 94 |
+
756,
|
| 95 |
+
825
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 75536,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01142/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 270,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9975023823785223,
|
| 108 |
+
0.03319271732179418,
|
| 109 |
+
-0.06234773986254607,
|
| 110 |
+
3.495374654113599
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.07063283336503111,
|
| 114 |
+
-0.46875954182659957,
|
| 115 |
+
0.8804972997104217,
|
| 116 |
+
5.940025996068705
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8827019516593989,
|
| 121 |
+
0.46993325540622055,
|
| 122 |
+
2.374381002403788
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
3.495374654113599,
|
| 133 |
+
5.940025996068705,
|
| 134 |
+
2.374381002403788
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 12,
|
| 138 |
+
"dist": 1.2868893968723192,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.08166639934259834,
|
| 143 |
+
0.6258614354376338,
|
| 144 |
+
-3.1223541721601658
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.0816663993425979,
|
| 148 |
+
-0.625861435437633,
|
| 149 |
+
-2.872161104342846
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
357,
|
| 154 |
+
166,
|
| 155 |
+
695,
|
| 156 |
+
527
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
198,
|
| 160 |
+
442,
|
| 161 |
+
655,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 63572,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01142/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01144/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1144,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "685df4a4-cd69-4f0b-82f5-675bd0738881",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "bb9f0b8a-b050-4b1c-b8da-43576a577465#756",
|
| 9 |
+
"category": "Bed",
|
| 10 |
+
"raw_cat": "front3d_cat17",
|
| 11 |
+
"center": [
|
| 12 |
+
4.287464141845703,
|
| 13 |
+
2.831418514251709,
|
| 14 |
+
0.3883081078529358
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
4.6970906257629395,
|
| 19 |
+
1.8849364817142487,
|
| 20 |
+
1.2916121184825897
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.997350704845228,
|
| 41 |
+
-0.05744701910138426,
|
| 42 |
+
0.04462523435335687,
|
| 43 |
+
4.613511427819739
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.07274318899200688,
|
| 47 |
+
0.787631471563867,
|
| 48 |
+
-0.6118374730738634,
|
| 49 |
+
0.6959894508889752
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.6134627168773197,
|
| 54 |
+
0.7897236826900264,
|
| 55 |
+
2.985414296089228
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
4.613511427819739,
|
| 66 |
+
0.6959894508889752,
|
| 67 |
+
2.985414296089228
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 4,
|
| 71 |
+
"dist": 1.3709778371156325,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.16984557054385796,
|
| 76 |
+
-0.10743376200761023,
|
| 77 |
+
-2.0613482991114274
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.16984557054385796,
|
| 81 |
+
0.1074337620076089,
|
| 82 |
+
-3.3720817219142307
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
405,
|
| 87 |
+
283,
|
| 88 |
+
771,
|
| 89 |
+
721
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
84,
|
| 93 |
+
279,
|
| 94 |
+
833,
|
| 95 |
+
739
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 98262,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01144/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 180,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.997350704845228,
|
| 108 |
+
0.05744701910138425,
|
| 109 |
+
-0.04462523435335687,
|
| 110 |
+
4.371043339788904
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.07274318899200687,
|
| 114 |
+
-0.787631471563867,
|
| 115 |
+
0.6118374730738635,
|
| 116 |
+
4.020365545076983
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.6134627168773198,
|
| 121 |
+
0.7897236826900264,
|
| 122 |
+
2.985414296089228
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
4.371043339788904,
|
| 133 |
+
4.020365545076983,
|
| 134 |
+
2.985414296089228
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 12,
|
| 138 |
+
"dist": 1.3709778371156325,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.16984557054385796,
|
| 143 |
+
0.6615770945346562,
|
| 144 |
+
-2.65872115205111
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.16984557054385796,
|
| 148 |
+
-0.6615770945346564,
|
| 149 |
+
-2.7747088689745487
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
294,
|
| 154 |
+
64,
|
| 155 |
+
580,
|
| 156 |
+
490
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
79,
|
| 160 |
+
367,
|
| 161 |
+
1004,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 83236,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01144/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 270,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.0727431889920066,
|
| 175 |
+
0.787631471563867,
|
| 176 |
+
-0.6118374730738635,
|
| 177 |
+
2.8300893367103175
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.997350704845228,
|
| 181 |
+
0.05744701910138404,
|
| 182 |
+
-0.04462523435335671,
|
| 183 |
+
2.236943453967562
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.6134627168773198,
|
| 188 |
+
0.7897236826900264,
|
| 189 |
+
2.985414296089228
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
2.8300893367103175,
|
| 200 |
+
2.236943453967562,
|
| 201 |
+
2.985414296089228
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 2,
|
| 205 |
+
"dist": 1.3709778371156325,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.4868860295051516,
|
| 210 |
+
0.41120273572200805,
|
| 211 |
+
-2.464228650736683
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.4868860295051509,
|
| 215 |
+
-0.41120273572200716,
|
| 216 |
+
-2.969201370288976
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
548,
|
| 221 |
+
125,
|
| 222 |
+
897,
|
| 223 |
+
570
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
0,
|
| 227 |
+
319,
|
| 228 |
+
726,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 100896,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01144/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_01148/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1148,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "b011f582-89dc-4638-805a-e85cac78c755",
|
| 6 |
+
"target_category": "others",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "f47e91bf-c4c3-4399-9917-ac2c0d393fee#420",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
3.248800277709961,
|
| 13 |
+
0.7421999573707581,
|
| 14 |
+
0.2590014934539795
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
2.878587245941162,
|
| 19 |
+
0.06904452666640282,
|
| 20 |
+
1.0330030620098114
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9978245343137506,
|
| 41 |
+
-0.05154999124710026,
|
| 42 |
+
0.04109497687030196,
|
| 43 |
+
3.208136387266065
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.06592570607545108,
|
| 47 |
+
-0.7802395919908058,
|
| 48 |
+
0.6219967687765541,
|
| 49 |
+
2.591846767248132
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.6233528515154516,
|
| 54 |
+
0.781940677102525,
|
| 55 |
+
3.394405438923013
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
3.208136387266065,
|
| 66 |
+
2.591846767248132,
|
| 67 |
+
3.394405438923013
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 1,
|
| 71 |
+
"dist": 1.0905385600266961,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.16251469947693753,
|
| 76 |
+
0.5133915409915576,
|
| 77 |
+
-3.4291942297594824
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.16251469947693709,
|
| 81 |
+
-0.5133915409915578,
|
| 82 |
+
-3.600503141594324
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
489,
|
| 87 |
+
263,
|
| 88 |
+
608,
|
| 89 |
+
512
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
230,
|
| 93 |
+
449,
|
| 94 |
+
719,
|
| 95 |
+
835
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 13835,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01148/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 180,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9978245343137505,
|
| 108 |
+
0.05154999124710041,
|
| 109 |
+
-0.041094976870302086,
|
| 110 |
+
2.9192511363850575
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.06592570607545127,
|
| 114 |
+
0.7802395919908058,
|
| 115 |
+
-0.6219967687765541,
|
| 116 |
+
-1.7806022832109711
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.6233528515154516,
|
| 121 |
+
0.781940677102525,
|
| 122 |
+
3.394405438923013
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
2.9192511363850575,
|
| 133 |
+
-1.7806022832109711,
|
| 134 |
+
3.394405438923013
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 9,
|
| 138 |
+
"dist": 1.0905385600266961,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.16251469947693753,
|
| 143 |
+
-0.030915456154847032,
|
| 144 |
+
-2.99527983099936
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.16251469947693709,
|
| 148 |
+
0.030915456154848253,
|
| 149 |
+
-4.034417540354445
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
400,
|
| 154 |
+
413,
|
| 155 |
+
536,
|
| 156 |
+
662
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
353,
|
| 160 |
+
344,
|
| 161 |
+
777,
|
| 162 |
+
692
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 18270,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01148/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 270,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.06592570607545134,
|
| 175 |
+
-0.7802395919908058,
|
| 176 |
+
0.6219967687765541,
|
| 177 |
+
5.249918287055113
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.9978245343137505,
|
| 181 |
+
0.05154999124710047,
|
| 182 |
+
-0.041094976870302134,
|
| 183 |
+
0.26117961657807626
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
-0.0,
|
| 187 |
+
0.6233528515154516,
|
| 188 |
+
0.781940677102525,
|
| 189 |
+
3.394405438923013
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
5.249918287055113,
|
| 200 |
+
0.26117961657807626,
|
| 201 |
+
3.394405438923013
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 11,
|
| 205 |
+
"dist": 1.0905385600266961,
|
| 206 |
+
"lr": "left",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
-0.34804877984051835,
|
| 210 |
+
0.3683148965664651,
|
| 211 |
+
-3.313541031711546
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
0.34804877984051874,
|
| 215 |
+
-0.36831489656646377,
|
| 216 |
+
-3.7161563396422586
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
365,
|
| 221 |
+
301,
|
| 222 |
+
491,
|
| 223 |
+
548
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
406,
|
| 227 |
+
410,
|
| 228 |
+
847,
|
| 229 |
+
826
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 14653,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01148/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_01151/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1151,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "11eb5631-12be-45e6-9428-dd65e897d733",
|
| 6 |
+
"target_category": "chair",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "f36889f8-d94b-4ab9-9da1-46e06a27ff90#347",
|
| 9 |
+
"category": "Bed",
|
| 10 |
+
"raw_cat": "front3d_cat17",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.7544971704483032,
|
| 13 |
+
1.8961994647979736,
|
| 14 |
+
0.394632488489151
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-2.264543294906616,
|
| 19 |
+
1.5186680555343628,
|
| 20 |
+
1.3042650520801544
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9825582726133322,
|
| 41 |
+
-0.056364232302200036,
|
| 42 |
+
0.1772069813412786,
|
| 43 |
+
-1.32731489490055
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.18595494324998363,
|
| 47 |
+
-0.2978202233299927,
|
| 48 |
+
0.9363353425224152,
|
| 49 |
+
5.312105335648657
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.9529565508944554,
|
| 54 |
+
0.303106931803519,
|
| 55 |
+
2.0163394042112452
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-1.32731489490055,
|
| 66 |
+
5.312105335648657,
|
| 67 |
+
2.0163394042112452
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 1,
|
| 71 |
+
"dist": 1.109102526730804,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "behind",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.2154731036080917,
|
| 76 |
+
0.504012578622872,
|
| 77 |
+
-3.9338474826959415
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.2154731036080917,
|
| 81 |
+
-0.5040125786228726,
|
| 82 |
+
-3.7656836826486906
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
494,
|
| 87 |
+
280,
|
| 88 |
+
629,
|
| 89 |
+
524
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
160,
|
| 93 |
+
491,
|
| 94 |
+
796,
|
| 95 |
+
848
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 9681,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01151/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 225,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.8262636188430508,
|
| 108 |
+
-0.22124491359009746,
|
| 109 |
+
0.5180145947624409,
|
| 110 |
+
0.056975461792891036
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.5632836161086043,
|
| 114 |
+
0.3245374403333006,
|
| 115 |
+
-0.7598598671107217,
|
| 116 |
+
-1.3238459753116083
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.9196336977473256,
|
| 121 |
+
0.3927771148725195,
|
| 122 |
+
2.416339404211245
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
0.056975461792891036,
|
| 133 |
+
-1.3238459753116083,
|
| 134 |
+
2.416339404211245
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 11,
|
| 138 |
+
"dist": 1.109102526730804,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.3170449069881913,
|
| 143 |
+
0.41342539578574033,
|
| 144 |
+
-3.7992902872778584
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.31704490698819154,
|
| 148 |
+
-0.4134253957857408,
|
| 149 |
+
-4.1792327712009705
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
511,
|
| 154 |
+
298,
|
| 155 |
+
517,
|
| 156 |
+
411
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
511,
|
| 160 |
+
576,
|
| 161 |
+
824,
|
| 162 |
+
844
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 580,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01151/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01168/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1168,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "6a335986-9e77-4217-a04e-65487aec0d7a",
|
| 6 |
+
"target_category": "chair",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "6c6ad156-abcc-4e30-a452-b07eaa23e30a#454",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
0.043572016060352325,
|
| 13 |
+
0.5718454718589783,
|
| 14 |
+
0.2623625695705414
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.04852854087948799,
|
| 19 |
+
0.0480700246989727,
|
| 20 |
+
0.9935971200466156
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.979036908860823,
|
| 41 |
+
0.09483587666740893,
|
| 42 |
+
-0.18025783640377094,
|
| 43 |
+
-0.34424434858815794
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.2036829180079779,
|
| 47 |
+
0.4558449203773171,
|
| 48 |
+
-0.866440233067436,
|
| 49 |
+
-1.332799611239228
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8849924096075183,
|
| 54 |
+
0.46560544985757907,
|
| 55 |
+
1.510760618593111
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-0.34424434858815794,
|
| 66 |
+
-1.332799611239228,
|
| 67 |
+
1.510760618593111
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 12,
|
| 71 |
+
"dist": 0.904172107204286,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.008257133443870857,
|
| 76 |
+
0.1998211063744494,
|
| 77 |
+
-1.490540244276659
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.008257133443871023,
|
| 81 |
+
-0.19982110637444916,
|
| 82 |
+
-2.30142900374035
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
0,
|
| 87 |
+
82,
|
| 88 |
+
782,
|
| 89 |
+
807
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
0,
|
| 93 |
+
0,
|
| 94 |
+
0,
|
| 95 |
+
0
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 283762,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01168/view_00_front/rgb.png",
|
| 99 |
+
"ok": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 225,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.8363092098227086,
|
| 108 |
+
0.2552719428769467,
|
| 109 |
+
-0.48520422581171485,
|
| 110 |
+
-0.9224180140525294
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.5482580647520989,
|
| 114 |
+
-0.38939012585953875,
|
| 115 |
+
0.7401273027779586,
|
| 116 |
+
1.7132277341548716
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8849924096075183,
|
| 121 |
+
0.46560544985757907,
|
| 122 |
+
1.510760618593111
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-0.9224180140525294,
|
| 133 |
+
1.7132277341548716,
|
| 134 |
+
1.510760618593111
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 0.904172107204286,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.18209432851159965,
|
| 143 |
+
0.4137896629978901,
|
| 144 |
+
-1.8972376928661117
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.18209432851159946,
|
| 148 |
+
-0.4137896629978901,
|
| 149 |
+
-1.8947315551508974
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
344,
|
| 154 |
+
80,
|
| 155 |
+
995,
|
| 156 |
+
631
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
297,
|
| 160 |
+
569,
|
| 161 |
+
548,
|
| 162 |
+
879
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 193700,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01168/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": false
|
| 170 |
+
}
|
data/batch_v5/pair_01172/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1172,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "5c2b4502-8d34-47cc-ac50-22589b794c7e",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "24caaf37-afd3-4cc9-84b5-f27e9cf84d8a#253",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.26089900732040405,
|
| 13 |
+
1.9098999500274658,
|
| 14 |
+
0.22242200374603271
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
1.0963629633188248,
|
| 19 |
+
1.29991914331913,
|
| 20 |
+
0.9598440080881119
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9356915680751974,
|
| 41 |
+
0.24385486753600946,
|
| 42 |
+
-0.25498253471948545,
|
| 43 |
+
-0.19908913783939075
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.3528190604728978,
|
| 47 |
+
-0.6467137662055693,
|
| 48 |
+
0.6762248259027689,
|
| 49 |
+
3.2407461035966403
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.722700566057066,
|
| 54 |
+
0.6911612632525035,
|
| 55 |
+
2.2631018805415164
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-0.19908913783939075,
|
| 66 |
+
3.2407461035966403,
|
| 67 |
+
2.2631018805415164
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 11,
|
| 71 |
+
"dist": 1.6607311203153643,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "behind",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.5273828632334585,
|
| 76 |
+
0.6291966114211544,
|
| 77 |
+
-2.5435143911507296
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.5273828632334586,
|
| 81 |
+
-0.6291966114211538,
|
| 82 |
+
-2.2946296528496646
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
178,
|
| 87 |
+
58,
|
| 88 |
+
470,
|
| 89 |
+
509
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
581,
|
| 93 |
+
596,
|
| 94 |
+
841,
|
| 95 |
+
942
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 86454,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01172/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 225,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.41215310269279315,
|
| 108 |
+
-0.6297271200307092,
|
| 109 |
+
0.6584630393868229,
|
| 110 |
+
2.0106014941010875
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.9111146030772989,
|
| 114 |
+
0.2848642591105897,
|
| 115 |
+
-0.2978632806182577,
|
| 116 |
+
0.8843568181484771
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.722700566057066,
|
| 121 |
+
0.6911612632525035,
|
| 122 |
+
2.2631018805415164
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
2.0106014941010875,
|
| 133 |
+
0.8843568181484771,
|
| 134 |
+
2.2631018805415164
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 6,
|
| 138 |
+
"dist": 1.6607311203153643,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.0018186558885284754,
|
| 143 |
+
-0.24776555125577004,
|
| 144 |
+
-1.626534396648779
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.0018186558885284754,
|
| 148 |
+
0.24776555125576938,
|
| 149 |
+
-3.211609647351615
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
382,
|
| 154 |
+
276,
|
| 155 |
+
590,
|
| 156 |
+
1008
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
398,
|
| 160 |
+
358,
|
| 161 |
+
628,
|
| 162 |
+
504
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 120147,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01172/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01174/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1174,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "6b39114f-2001-42fb-939a-46ddbb667a36",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "0693202e-7fe9-47bc-9ceb-bc3cf22f7f74#320",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
0.9946100115776062,
|
| 13 |
+
1.3978500366210938,
|
| 14 |
+
0.21195000410079956
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
1.8870035111904144,
|
| 19 |
+
2.031347334384918,
|
| 20 |
+
0.5543209910392761
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.997784126940618,
|
| 41 |
+
0.033873065582813416,
|
| 42 |
+
-0.05726649503305782,
|
| 43 |
+
1.1978468073281283
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.06653447245863467,
|
| 47 |
+
-0.5079773825570262,
|
| 48 |
+
0.858796915915028,
|
| 49 |
+
5.358147310464261
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8607041270021512,
|
| 54 |
+
0.5091054957093518,
|
| 55 |
+
2.5430764504035963
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
1.1978468073281283,
|
| 66 |
+
5.358147310464261,
|
| 67 |
+
2.5430764504035963
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.146692145749019,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.4662827387046675,
|
| 76 |
+
0.0015529628933956263,
|
| 77 |
+
-3.9089974822662095
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.4662827387046675,
|
| 81 |
+
-0.0015529628933953488,
|
| 82 |
+
-4.5762417109349895
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
327,
|
| 87 |
+
443,
|
| 88 |
+
494,
|
| 89 |
+
595
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
538,
|
| 93 |
+
424,
|
| 94 |
+
669,
|
| 95 |
+
621
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 11890,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01174/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.06653447245863478,
|
| 108 |
+
0.5079773825570261,
|
| 109 |
+
-0.8587969159150282,
|
| 110 |
+
-2.2027418635772453
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.9977841269406178,
|
| 114 |
+
0.03387306558281348,
|
| 115 |
+
-0.057266495033057925,
|
| 116 |
+
1.4716387314471235
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.860704127002151,
|
| 121 |
+
0.5091054957093518,
|
| 122 |
+
2.5430764504035963
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-2.2027418635772453,
|
| 133 |
+
1.4716387314471235,
|
| 134 |
+
2.5430764504035963
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 11,
|
| 138 |
+
"dist": 1.146692145749019,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.2863593087231324,
|
| 143 |
+
0.38472716554082753,
|
| 144 |
+
-4.556799598642666
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.28635930872313264,
|
| 148 |
+
-0.384727165540827,
|
| 149 |
+
-3.928439594558533
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
360,
|
| 154 |
+
388,
|
| 155 |
+
546,
|
| 156 |
+
463
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
476,
|
| 160 |
+
522,
|
| 161 |
+
726,
|
| 162 |
+
673
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 5670,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01174/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.6584929456618397,
|
| 175 |
+
-0.38314612626865024,
|
| 176 |
+
0.6477546498782706,
|
| 177 |
+
4.188983332746721
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.7525868989781801,
|
| 181 |
+
0.33524237752228214,
|
| 182 |
+
-0.5667675959329487,
|
| 183 |
+
-0.6899806237203325
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
-0.0,
|
| 187 |
+
0.8607041270021512,
|
| 188 |
+
0.5091054957093518,
|
| 189 |
+
2.5430764504035963
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
4.188983332746721,
|
| 200 |
+
-0.6899806237203325,
|
| 201 |
+
2.5430764504035963
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 3,
|
| 205 |
+
"dist": 1.146692145749019,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.5321982955423246,
|
| 210 |
+
0.08256907459803009,
|
| 211 |
+
-4.045964971883834
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.5321982955423246,
|
| 215 |
+
-0.08256907459803015,
|
| 216 |
+
-4.439274221317365
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
593,
|
| 221 |
+
425,
|
| 222 |
+
657,
|
| 223 |
+
575
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
266,
|
| 227 |
+
438,
|
| 228 |
+
534,
|
| 229 |
+
641
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 7194,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01174/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_01179/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1179,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "4a60daea-bd12-4fa5-8cdd-e6565f3055dd",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "82c830e5-5bf1-4f4a-be30-9c6d47c6af2b#367",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
3.7384512424468994,
|
| 13 |
+
4.7975263595581055,
|
| 14 |
+
0.4271659851074219
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
3.1539876461029053,
|
| 19 |
+
4.452614784240723,
|
| 20 |
+
1.369331955909729
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.146930079170512,
|
| 41 |
+
0.5723595160322422,
|
| 42 |
+
-0.8067317622619583,
|
| 43 |
+
1.5774255780779232
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9891468808195004,
|
| 47 |
+
-0.08501955638270801,
|
| 48 |
+
0.11983373146798221,
|
| 49 |
+
4.902665372063168
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8155833859513233,
|
| 54 |
+
0.5786395601410044,
|
| 55 |
+
2.238667324309914
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
1.5774255780779232,
|
| 66 |
+
4.902665372063168,
|
| 67 |
+
2.238667324309914
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 1,
|
| 71 |
+
"dist": 1.1611366873788493,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.2135217456834173,
|
| 76 |
+
0.23160792028894672,
|
| 77 |
+
-1.8288257719273742
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.21352174568341642,
|
| 81 |
+
-0.23160792028894672,
|
| 82 |
+
-2.8041735808120136
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
439,
|
| 87 |
+
108,
|
| 88 |
+
836,
|
| 89 |
+
675
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
281,
|
| 93 |
+
435,
|
| 94 |
+
615,
|
| 95 |
+
754
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 89192,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01179/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 270,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9891468808195005,
|
| 108 |
+
-0.09955007185355605,
|
| 109 |
+
0.10806586583655678,
|
| 110 |
+
3.7238142444386555
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.1469300791705118,
|
| 114 |
+
-0.6701802899393288,
|
| 115 |
+
0.7275094025590214,
|
| 116 |
+
6.493864438096393
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7354917825311096,
|
| 121 |
+
0.6775336433190686,
|
| 122 |
+
2.638667324309914
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
3.7238142444386555,
|
| 133 |
+
6.493864438096393,
|
| 134 |
+
2.638667324309914
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.1611366873788493,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.26372122910400053,
|
| 143 |
+
0.4911458309335046,
|
| 144 |
+
-2.40662453762213
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.26372122910399964,
|
| 148 |
+
-0.49114583093350417,
|
| 149 |
+
-2.7308867017473624
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
480,
|
| 154 |
+
100,
|
| 155 |
+
771,
|
| 156 |
+
521
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
257,
|
| 160 |
+
526,
|
| 161 |
+
583,
|
| 162 |
+
802
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 57549,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01179/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_01195/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1195,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "0b4d5b33-7730-4198-8103-dc845192d495",
|
| 6 |
+
"target_category": "lighting",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "71077ab4-63f1-4875-a2b2-4199ea4de5d6#438",
|
| 9 |
+
"category": "Bed",
|
| 10 |
+
"raw_cat": "front3d_cat17",
|
| 11 |
+
"center": [
|
| 12 |
+
4.719888210296631,
|
| 13 |
+
0.41356363892555237,
|
| 14 |
+
0.3883081078529358
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
4.799513578414917,
|
| 19 |
+
1.144272342324257,
|
| 20 |
+
1.291612148284912
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.984892097334665,
|
| 41 |
+
0.13992857135737066,
|
| 42 |
+
-0.10201740795379004,
|
| 43 |
+
4.4195456423601795
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.1731691560518928,
|
| 47 |
+
-0.7958377072641382,
|
| 48 |
+
0.5802196024686128,
|
| 49 |
+
2.713536297922942
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5891199696279571,
|
| 54 |
+
0.8080455812548911,
|
| 55 |
+
3.5342154892734103
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
4.4195456423601795,
|
| 66 |
+
2.713536297922942,
|
| 67 |
+
3.5342154892734103
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.1645744278195886,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.10247930264719507,
|
| 76 |
+
-0.019114613161041127,
|
| 77 |
+
-2.7614067726208598
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.10247930264719507,
|
| 81 |
+
0.01911461316104146,
|
| 82 |
+
-3.9071659507651657
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
363,
|
| 87 |
+
392,
|
| 88 |
+
599,
|
| 89 |
+
633
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
207,
|
| 93 |
+
249,
|
| 94 |
+
807,
|
| 95 |
+
668
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 31111,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01195/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.17316915605189273,
|
| 108 |
+
0.7958377072641382,
|
| 109 |
+
-0.5802196024686128,
|
| 110 |
+
2.8250825870577367
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.984892097334665,
|
| 114 |
+
0.1399285713573706,
|
| 115 |
+
-0.10201740795379001,
|
| 116 |
+
0.43876273862931037
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.5891199696279571,
|
| 121 |
+
0.8080455812548911,
|
| 122 |
+
3.5342154892734103
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
2.8250825870577367,
|
| 133 |
+
0.43876273862931037,
|
| 134 |
+
3.5342154892734103
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.1645744278195886,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.3529402848168394,
|
| 143 |
+
0.34888517210619696,
|
| 144 |
+
-3.0297035461556483
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.3529402848168394,
|
| 148 |
+
-0.34888517210619696,
|
| 149 |
+
-3.6388691772303763
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
314,
|
| 154 |
+
281,
|
| 155 |
+
499,
|
| 156 |
+
544
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
323,
|
| 160 |
+
328,
|
| 161 |
+
897,
|
| 162 |
+
985
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 29924,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01195/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.984892097334665,
|
| 175 |
+
-0.13992857135737102,
|
| 176 |
+
0.1020174079537903,
|
| 177 |
+
5.099856146351369
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.17316915605189323,
|
| 181 |
+
0.7958377072641382,
|
| 182 |
+
-0.5802196024686128,
|
| 183 |
+
-1.1557003166731323
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
-0.0,
|
| 187 |
+
0.5891199696279572,
|
| 188 |
+
0.8080455812548911,
|
| 189 |
+
3.5342154892734103
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
5.099856146351369,
|
| 200 |
+
-1.1557003166731323,
|
| 201 |
+
3.5342154892734103
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 12,
|
| 205 |
+
"dist": 1.1645744278195886,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.10247930264719596,
|
| 210 |
+
0.5512690620251377,
|
| 211 |
+
-3.1772551123644175
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.10247930264719418,
|
| 215 |
+
-0.5512690620251388,
|
| 216 |
+
-3.4913176110216075
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
442,
|
| 221 |
+
224,
|
| 222 |
+
653,
|
| 223 |
+
475
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
81,
|
| 227 |
+
463,
|
| 228 |
+
801,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 29968,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01195/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_01199/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 1199,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "64184c4a-d0f6-4502-badc-6fcaf1ee71b0",
|
| 6 |
+
"target_category": "others",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "bec925cf-884c-4061-9145-7fc7b1cba882#344",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
4.3730950355529785,
|
| 13 |
+
1.3411165475845337,
|
| 14 |
+
0.42766499519348145
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
3.0897028531347,
|
| 19 |
+
1.5814998235021318,
|
| 20 |
+
1.3182348566395896
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.02558353610983263,
|
| 41 |
+
0.6622621127780356,
|
| 42 |
+
-0.7488353468279189,
|
| 43 |
+
1.1373635650850131
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9996726877734117,
|
| 47 |
+
-0.016948554145425714,
|
| 48 |
+
0.01916412878955584,
|
| 49 |
+
1.5276945123952412
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.7490805300441017,
|
| 54 |
+
0.6624789502383059,
|
| 55 |
+
3.1678387051548373
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
1.1373635650850131,
|
| 66 |
+
1.5276945123952412,
|
| 67 |
+
3.1678387051548373
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 8,
|
| 71 |
+
"dist": 1.5805044420530325,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.10373544264517398,
|
| 76 |
+
-0.09345381168266753,
|
| 77 |
+
-2.6862731519019567
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.10373544264517398,
|
| 81 |
+
0.09345381168266709,
|
| 82 |
+
-4.241913104922618
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
312,
|
| 87 |
+
345,
|
| 88 |
+
664,
|
| 89 |
+
720
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
119,
|
| 93 |
+
356,
|
| 94 |
+
960,
|
| 95 |
+
695
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 62927,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01199/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 180,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.02558353610983323,
|
| 108 |
+
-0.6622621127780356,
|
| 109 |
+
0.7488353468279189,
|
| 110 |
+
6.325434323602665
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.9996726877734117,
|
| 114 |
+
0.01694855414542611,
|
| 115 |
+
-0.019164128789556287,
|
| 116 |
+
1.3949218586914227
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.7490805300441017,
|
| 121 |
+
0.6624789502383059,
|
| 122 |
+
3.1678387051548373
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
6.325434323602665,
|
| 133 |
+
1.3949218586914227,
|
| 134 |
+
3.1678387051548373
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 12,
|
| 138 |
+
"dist": 1.5805044420530325,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.10373544264517354,
|
| 143 |
+
0.7605623555360199,
|
| 144 |
+
-3.6519293179979293
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.10373544264517376,
|
| 148 |
+
-0.7605623555360195,
|
| 149 |
+
-3.2762569388266485
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
383,
|
| 154 |
+
177,
|
| 155 |
+
588,
|
| 156 |
+
310
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
0,
|
| 160 |
+
0,
|
| 161 |
+
0,
|
| 162 |
+
0
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 19415,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01199/view_01_right/rgb.png",
|
| 166 |
+
"ok": false
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 270,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.9996726877734117,
|
| 175 |
+
-0.01694855414542611,
|
| 176 |
+
0.019164128789556287,
|
| 177 |
+
3.797785271195749
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.02558353610983323,
|
| 181 |
+
-0.6622621127780356,
|
| 182 |
+
0.7488353468279189,
|
| 183 |
+
4.0553435648021585
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.7490805300441017,
|
| 188 |
+
0.6624789502383059,
|
| 189 |
+
3.1678387051548373
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
3.797785271195749,
|
| 200 |
+
4.0553435648021585,
|
| 201 |
+
3.1678387051548373
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 2,
|
| 205 |
+
"dist": 1.5805044420530325,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.6445609833425507,
|
| 210 |
+
0.2648317247805952,
|
| 211 |
+
-3.091395034588936
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.6445609833425512,
|
| 215 |
+
-0.2648317247805962,
|
| 216 |
+
-3.8367912222356395
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
475,
|
| 221 |
+
233,
|
| 222 |
+
841,
|
| 223 |
+
581
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
36,
|
| 227 |
+
312,
|
| 228 |
+
579,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 75138,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_01199/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": false
|
| 237 |
+
}
|
data/batch_v5/pair_02009/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2009,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "44674565-5d1d-4773-b12a-27f4d366ebf0",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "f59de3b0-18c0-48a3-b804-d01778b0d671#419",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.9740409851074219,
|
| 13 |
+
0.3769999146461487,
|
| 14 |
+
0.3500739336013794
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.0637686401605606,
|
| 19 |
+
1.0913640856742859,
|
| 20 |
+
0.8817272186279297
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9351415397122269,
|
| 41 |
+
0.25110279654139694,
|
| 42 |
+
-0.24991535821900812,
|
| 43 |
+
-1.6743125902340212
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.3542743297285951,
|
| 47 |
+
-0.6628102464089282,
|
| 48 |
+
0.6596758875013474,
|
| 49 |
+
2.4641945549896755
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.7054289211709607,
|
| 54 |
+
0.7087806693015649,
|
| 55 |
+
2.4746913546538036
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-1.6743125902340212,
|
| 66 |
+
2.4641945549896755,
|
| 67 |
+
2.4746913546538036
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 8,
|
| 71 |
+
"dist": 0.8949985678254324,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.08458641518597865,
|
| 76 |
+
-0.060487577021268724,
|
| 77 |
+
-2.187269654731386
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.08458641518597843,
|
| 81 |
+
0.060487577021268946,
|
| 82 |
+
-3.057768363505788
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
296,
|
| 87 |
+
405,
|
| 88 |
+
571,
|
| 89 |
+
651
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
150,
|
| 93 |
+
218,
|
| 94 |
+
783,
|
| 95 |
+
818
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 26316,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02009/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.3542743297285951,
|
| 108 |
+
0.6628102464089282,
|
| 109 |
+
-0.6596758875013474,
|
| 110 |
+
-2.7489173674634495
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.9351415397122269,
|
| 114 |
+
0.25110279654139694,
|
| 115 |
+
-0.2499153582190081,
|
| 116 |
+
0.0787742225601874
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7054289211709607,
|
| 121 |
+
0.7087806693015649,
|
| 122 |
+
2.4746913546538036
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-2.7489173674634495,
|
| 133 |
+
0.0787742225601874,
|
| 134 |
+
2.4746913546538036
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 0.8949985678254324,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.34990990783128484,
|
| 143 |
+
0.2474750176159769,
|
| 144 |
+
-2.4937759271302036
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.3499099078312853,
|
| 148 |
+
-0.24747501761597568,
|
| 149 |
+
-2.75126209110697
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
291,
|
| 154 |
+
325,
|
| 155 |
+
548,
|
| 156 |
+
511
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
156,
|
| 160 |
+
320,
|
| 161 |
+
1023,
|
| 162 |
+
830
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 20119,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02009/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02013/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2013,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "a306b4cb-fab4-476b-b435-c86b7755427e",
|
| 6 |
+
"target_category": "lighting",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "863e7831-9dbc-442a-842c-0fdd6b3d40b0#461",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.4437777996063232,
|
| 13 |
+
-1.1930170059204102,
|
| 14 |
+
0.183445006608963
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.5652251541614532,
|
| 19 |
+
-0.5048066414892673,
|
| 20 |
+
0.8818558106819788
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.01700351556332193,
|
| 41 |
+
0.8051497605269425,
|
| 42 |
+
-0.5928277520341764,
|
| 43 |
+
-2.5109010593546
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9998554297789695,
|
| 47 |
+
0.01369235599085682,
|
| 48 |
+
-0.01008161340916118,
|
| 49 |
+
-0.8745296160198585
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5929134696655378,
|
| 54 |
+
0.8052661780362896,
|
| 55 |
+
2.578864726732456
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-2.5109010593546,
|
| 66 |
+
-0.8745296160198585,
|
| 67 |
+
2.578864726732456
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 11,
|
| 71 |
+
"dist": 1.31653557026559,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.336586193063311,
|
| 76 |
+
0.565443423245734,
|
| 77 |
+
-2.5237219610818906
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.33658619306331106,
|
| 81 |
+
-0.5654434232457335,
|
| 82 |
+
-2.5583598992958865
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
270,
|
| 87 |
+
142,
|
| 88 |
+
528,
|
| 89 |
+
453
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
391,
|
| 93 |
+
545,
|
| 94 |
+
870,
|
| 95 |
+
881
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 42187,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02013/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9998554297789695,
|
| 108 |
+
-0.013692355990856761,
|
| 109 |
+
0.010081613409161137,
|
| 110 |
+
-0.9788836845688687
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.017003515563321858,
|
| 114 |
+
0.8051497605269425,
|
| 115 |
+
-0.5928277520341764,
|
| 116 |
+
-2.3553114061755505
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.5929134696655378,
|
| 121 |
+
0.8052661780362896,
|
| 122 |
+
2.578864726732456
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-0.9788836845688687,
|
| 133 |
+
-2.3553114061755505,
|
| 134 |
+
2.578864726732456
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.31653557026559,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.44506381426858765,
|
| 143 |
+
0.47809006381529207,
|
| 144 |
+
-2.4594041183120074
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.44506381426858765,
|
| 148 |
+
-0.47809006381529234,
|
| 149 |
+
-2.622677742065772
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
565,
|
| 154 |
+
160,
|
| 155 |
+
774,
|
| 156 |
+
494
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
226,
|
| 160 |
+
499,
|
| 161 |
+
562,
|
| 162 |
+
953
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 31506,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02013/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02014/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2014,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "0f01a988-ab48-456d-b60b-ea35beb99dce",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "5738a0e6-b70a-46b1-bf0b-883209231ce8#413",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.8631476163864136,
|
| 13 |
+
2.375995397567749,
|
| 14 |
+
0.35017600655555725
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.4133838415145874,
|
| 19 |
+
0.7937455922365189,
|
| 20 |
+
1.2152230739593506
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.4718303718795196,
|
| 41 |
+
-0.6006020850301728,
|
| 42 |
+
0.6454868206473648,
|
| 43 |
+
0.3776065011476506
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.8816893444813962,
|
| 47 |
+
0.3214083360597772,
|
| 48 |
+
-0.34542811312811683,
|
| 49 |
+
0.5060894594476713
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.7321023268428358,
|
| 54 |
+
0.6811946733726751,
|
| 55 |
+
2.91008832871569
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
0.3776065011476506,
|
| 66 |
+
0.5060894594476713,
|
| 67 |
+
2.91008832871569
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.8585231579083359,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.5914202922562994,
|
| 76 |
+
-0.07268718362329363,
|
| 77 |
+
-2.4099583608986057
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.5914202922562998,
|
| 81 |
+
0.07268718362329452,
|
| 82 |
+
-3.836093969267993
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
69,
|
| 87 |
+
294,
|
| 88 |
+
451,
|
| 89 |
+
772
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
463,
|
| 93 |
+
338,
|
| 94 |
+
857,
|
| 95 |
+
672
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 112650,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02014/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.8816893444813962,
|
| 108 |
+
-0.32140833605977703,
|
| 109 |
+
0.3454281131281168,
|
| 110 |
+
-0.5594846934960378
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.47183037187951943,
|
| 114 |
+
-0.6006020850301726,
|
| 115 |
+
0.645486820647365,
|
| 116 |
+
3.6007427250002855
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7321023268428359,
|
| 121 |
+
0.681194673372675,
|
| 122 |
+
2.91008832871569
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-0.5594846934960378,
|
| 133 |
+
3.6007427250002855,
|
| 134 |
+
2.91008832871569
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 11,
|
| 138 |
+
"dist": 1.8585231579083359,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.5715527209469751,
|
| 143 |
+
0.7195238382469458,
|
| 144 |
+
-3.2613736099201485
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.5715527209469755,
|
| 148 |
+
-0.7195238382469469,
|
| 149 |
+
-2.9846787202464515
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
223,
|
| 154 |
+
143,
|
| 155 |
+
466,
|
| 156 |
+
488
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
474,
|
| 160 |
+
492,
|
| 161 |
+
968,
|
| 162 |
+
1016
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 57284,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02014/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.28981405885693845,
|
| 175 |
+
0.7097546269610621,
|
| 176 |
+
-0.6420717878837465,
|
| 177 |
+
-3.8265160384438475
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.957082969908496,
|
| 181 |
+
0.21492062412493215,
|
| 182 |
+
-0.19442560026108346,
|
| 183 |
+
0.9222469565793788
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.6708632459995952,
|
| 188 |
+
0.741581084687903,
|
| 189 |
+
3.3100883287156897
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-3.8265160384438475,
|
| 200 |
+
0.9222469565793788,
|
| 201 |
+
3.3100883287156897
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 2,
|
| 205 |
+
"dist": 1.8585231579083359,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.822346103972988,
|
| 210 |
+
0.27974604407617554,
|
| 211 |
+
-3.07793259708268
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.8223461039729876,
|
| 215 |
+
-0.2797460440761754,
|
| 216 |
+
-3.738284376741285
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
606,
|
| 221 |
+
282,
|
| 222 |
+
929,
|
| 223 |
+
550
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
203,
|
| 227 |
+
419,
|
| 228 |
+
498,
|
| 229 |
+
569
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 68292,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02014/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_02020/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2020,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "35b38447-4597-4297-838d-8392f62e37c3",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "9f787e94-23c0-44ec-a98b-ca7d2503d030#840",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.3917741775512695,
|
| 13 |
+
-3.077136993408203,
|
| 14 |
+
0.18296650052070618
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.9222106039524078,
|
| 19 |
+
-4.013986647129059,
|
| 20 |
+
0.8809330314397812
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.2157449819407931,
|
| 41 |
+
-0.6851305343162825,
|
| 42 |
+
0.6957372016177173,
|
| 43 |
+
-0.12440364389458836
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9764497441073795,
|
| 47 |
+
0.15137847661404819,
|
| 48 |
+
-0.15372200249360277,
|
| 49 |
+
-3.884184809837482
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.7125171631374893,
|
| 54 |
+
0.7016546816166087,
|
| 55 |
+
2.0775736980122503
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-0.12440364389458836,
|
| 66 |
+
-3.884184809837482,
|
| 67 |
+
2.0775736980122503
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 10,
|
| 71 |
+
"dist": 1.283046123260308,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.5146128009387345,
|
| 76 |
+
0.35945622570987157,
|
| 77 |
+
-2.0704763109970648
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.5146128009387345,
|
| 81 |
+
-0.359456225709872,
|
| 82 |
+
-2.3351778448931153
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
145,
|
| 87 |
+
97,
|
| 88 |
+
380,
|
| 89 |
+
576
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
481,
|
| 93 |
+
413,
|
| 94 |
+
1023,
|
| 95 |
+
978
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 48513,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02020/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9764497441073794,
|
| 108 |
+
-0.1513784766140483,
|
| 109 |
+
0.15372200249360288,
|
| 110 |
+
-1.3183694011829876
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.21574498194079325,
|
| 114 |
+
-0.6851305343162823,
|
| 115 |
+
0.6957372016177173,
|
| 116 |
+
-2.0129730734113807
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7125171631374893,
|
| 121 |
+
0.7016546816166087,
|
| 122 |
+
2.0775736980122503
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-1.3183694011829876,
|
| 133 |
+
-2.0129730734113807,
|
| 134 |
+
2.0775736980122503
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 12,
|
| 138 |
+
"dist": 1.283046123260308,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.15791195060069008,
|
| 143 |
+
0.6097370472861852,
|
| 144 |
+
-2.3246317889686585
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.15791195060068997,
|
| 148 |
+
-0.6097370472861865,
|
| 149 |
+
-2.0810223669215215
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
473,
|
| 154 |
+
58,
|
| 155 |
+
687,
|
| 156 |
+
456
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
95,
|
| 160 |
+
533,
|
| 161 |
+
822,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 33751,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02020/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.2157449819407931,
|
| 175 |
+
0.6851305343162825,
|
| 176 |
+
-0.6957372016177173,
|
| 177 |
+
-3.189581137609089
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.9764497441073795,
|
| 181 |
+
-0.15137847661404819,
|
| 182 |
+
0.15372200249360277,
|
| 183 |
+
-3.20693883069978
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.7125171631374893,
|
| 188 |
+
0.7016546816166087,
|
| 189 |
+
2.0775736980122503
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-3.189581137609089,
|
| 200 |
+
-3.20693883069978,
|
| 201 |
+
2.0775736980122503
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 3,
|
| 205 |
+
"dist": 1.283046123260308,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.514612800938735,
|
| 210 |
+
0.13785690686550195,
|
| 211 |
+
-1.8454463608620433
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.5146128009387341,
|
| 215 |
+
-0.1378569068655024,
|
| 216 |
+
-2.5602077950281377
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
677,
|
| 221 |
+
159,
|
| 222 |
+
901,
|
| 223 |
+
681
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
122,
|
| 227 |
+
355,
|
| 228 |
+
551,
|
| 229 |
+
842
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 55682,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02020/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_02021/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2021,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "874d4496-7e8a-4cbd-9fed-35bb923ff0ae",
|
| 6 |
+
"target_category": "lighting",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "df5f6372-1d1d-4884-a9f0-c8c33595daaf#543",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
4.828725337982178,
|
| 13 |
+
1.2235809564590454,
|
| 14 |
+
0.3682895600795746
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
6.406731128692627,
|
| 19 |
+
2.077170640230179,
|
| 20 |
+
1.2518742084503174
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.009174869238707624,
|
| 41 |
+
-0.4914731532704786,
|
| 42 |
+
0.8708443956234807,
|
| 43 |
+
9.016626058786926
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9999579100014423,
|
| 47 |
+
-0.004509391715882769,
|
| 48 |
+
0.007990219765445209,
|
| 49 |
+
1.6815615540572522
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8708810510056614,
|
| 54 |
+
0.49149384024550563,
|
| 55 |
+
2.728377911922406
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
9.016626058786926,
|
| 66 |
+
1.6815615540572522,
|
| 67 |
+
2.728377911922406
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 1.9998598587382723,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.4195378796974414,
|
| 76 |
+
-0.004949762431360583,
|
| 77 |
+
-2.9953438448552356
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.4195378796974414,
|
| 81 |
+
0.00494976243135925,
|
| 82 |
+
-4.8106381251293895
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
595,
|
| 87 |
+
364,
|
| 88 |
+
674,
|
| 89 |
+
652
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
327,
|
| 93 |
+
427,
|
| 94 |
+
538,
|
| 95 |
+
626
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 9250,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02021/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9999579100014423,
|
| 108 |
+
0.0037419248739195585,
|
| 109 |
+
-0.008377125031018957,
|
| 110 |
+
5.5865424776247625
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.009174869238707561,
|
| 114 |
+
-0.4078278696900649,
|
| 115 |
+
0.9130127329224473,
|
| 116 |
+
5.049273623794136
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.9130511632445913,
|
| 121 |
+
0.40784503588703713,
|
| 122 |
+
2.328377911922406
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
5.5865424776247625,
|
| 133 |
+
5.049273623794136,
|
| 134 |
+
2.328377911922406
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.9998598587382723,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.7928854730905508,
|
| 143 |
+
0.23227255390881052,
|
| 144 |
+
-3.1594853820048088
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.7928854730905526,
|
| 148 |
+
-0.2322725539088103,
|
| 149 |
+
-4.285970092794646
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
0,
|
| 154 |
+
0,
|
| 155 |
+
0,
|
| 156 |
+
0
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
0,
|
| 160 |
+
0,
|
| 161 |
+
0,
|
| 162 |
+
0
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 0,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02021/view_01_right/rgb.png",
|
| 166 |
+
"ok": false
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 270,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.9999579100014423,
|
| 175 |
+
-0.0037419248739196656,
|
| 176 |
+
0.008377125031019197,
|
| 177 |
+
5.648913989050043
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.009174869238707823,
|
| 181 |
+
0.40782786969006496,
|
| 182 |
+
-0.9130127329224473,
|
| 183 |
+
-1.7485220271049111
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
-0.0,
|
| 187 |
+
0.9130511632445913,
|
| 188 |
+
0.4078450358870372,
|
| 189 |
+
2.328377911922406
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
5.648913989050043,
|
| 200 |
+
-1.7485220271049111,
|
| 201 |
+
2.328377911922406
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 2,
|
| 205 |
+
"dist": 1.9998598587382723,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.7928854730905517,
|
| 210 |
+
0.5744854371111592,
|
| 211 |
+
-3.9256044801706436
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.7928854730905526,
|
| 215 |
+
-0.5744854371111595,
|
| 216 |
+
-3.5198509946288086
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
658,
|
| 221 |
+
263,
|
| 222 |
+
690,
|
| 223 |
+
490
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
166,
|
| 227 |
+
548,
|
| 228 |
+
454,
|
| 229 |
+
829
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 2133,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02021/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": false
|
| 237 |
+
}
|
data/batch_v5/pair_02032/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2032,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "9cee1f25-d93a-4bc8-9348-591c79520972",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "37301a61-1ddf-4bd9-b965-ecbebc50ba71#645",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-6.660654067993164,
|
| 13 |
+
-0.9036864638328552,
|
| 14 |
+
0.3447299897670746
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-5.629963040351868,
|
| 19 |
+
-0.19344061613082886,
|
| 20 |
+
0.9466072022914886
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.2134277969969538,
|
| 41 |
+
0.7843089466111681,
|
| 42 |
+
-0.5825015465513435,
|
| 43 |
+
-8.281632669807038
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9769588402123331,
|
| 47 |
+
-0.17134123132950171,
|
| 48 |
+
0.12725410397100403,
|
| 49 |
+
-0.08185918059220293
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5962395984100436,
|
| 54 |
+
0.8028065403868045,
|
| 55 |
+
3.589961160695083
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-8.281632669807038,
|
| 66 |
+
-0.08185918059220293,
|
| 67 |
+
3.589961160695083
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 11,
|
| 71 |
+
"dist": 1.3888950059649579,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "behind",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.45692953752530263,
|
| 76 |
+
0.5227744117833537,
|
| 77 |
+
-3.6809027020638867
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.45692953752530285,
|
| 81 |
+
-0.5227744117833568,
|
| 82 |
+
-3.654096246119064
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
372,
|
| 87 |
+
256,
|
| 88 |
+
490,
|
| 89 |
+
499
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
392,
|
| 93 |
+
513,
|
| 94 |
+
884,
|
| 95 |
+
767
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 12665,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02032/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9769588402123333,
|
| 108 |
+
0.17134123132950135,
|
| 109 |
+
-0.12725410397100376,
|
| 110 |
+
-6.612012913562154
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.21342779699695336,
|
| 114 |
+
0.7843089466111682,
|
| 115 |
+
-0.5825015465513435,
|
| 116 |
+
-2.6848876556163646
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.5962395984100436,
|
| 121 |
+
0.8028065403868045,
|
| 122 |
+
3.589961160695083
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-6.612012913562154,
|
| 133 |
+
-2.6848876556163646,
|
| 134 |
+
3.589961160695083
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.3888950059649579,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.42767825219021116,
|
| 143 |
+
0.5462575349650869,
|
| 144 |
+
-3.6983434766850585
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.4276782521902103,
|
| 148 |
+
-0.5462575349650873,
|
| 149 |
+
-3.6366554714978907
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
509,
|
| 154 |
+
306,
|
| 155 |
+
695,
|
| 156 |
+
490
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
315,
|
| 160 |
+
439,
|
| 161 |
+
517,
|
| 162 |
+
882
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 20885,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02032/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02044/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2044,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "c4bcf25e-e3a7-4e06-8dfa-17e3636a2968",
|
| 6 |
+
"target_category": "chair",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "133d45e4-e0c2-4d65-a627-10a56a7c2504#440",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
1.6807035207748413,
|
| 13 |
+
-2.8092896938323975,
|
| 14 |
+
0.46570301055908203
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
1.885182648897171,
|
| 19 |
+
-4.588320255279541,
|
| 20 |
+
1.4464060962200165
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.8869310784402962,
|
| 41 |
+
0.22295740173389622,
|
| 42 |
+
-0.40452844042020475,
|
| 43 |
+
0.6897396517452281
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.4619017883671085,
|
| 47 |
+
0.42811665541534055,
|
| 48 |
+
-0.7767643576138452,
|
| 49 |
+
-5.797944064910013
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8757888594678814,
|
| 54 |
+
0.48269438947635124,
|
| 55 |
+
2.2604947632325763
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
0.6897396517452281,
|
| 66 |
+
-5.797944064910013,
|
| 67 |
+
2.2604947632325763
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 2.0417002705160923,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.501548145758123,
|
| 76 |
+
0.07142317906708123,
|
| 77 |
+
-1.8161393847943996
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.5015481457581235,
|
| 81 |
+
-0.07142317906708096,
|
| 82 |
+
-3.588689170425158
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
533,
|
| 87 |
+
231,
|
| 88 |
+
1023,
|
| 89 |
+
790
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
169,
|
| 93 |
+
372,
|
| 94 |
+
571,
|
| 95 |
+
679
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 99154,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02044/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 270,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.4619017883671086,
|
| 108 |
+
0.42811665541534055,
|
| 109 |
+
-0.7767643576138451,
|
| 110 |
+
-0.31619600551803684
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.8869310784402962,
|
| 114 |
+
-0.22295740173389628,
|
| 115 |
+
0.4045284404202048,
|
| 116 |
+
-2.605601541465191
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8757888594678814,
|
| 121 |
+
0.48269438947635124,
|
| 122 |
+
2.2604947632325763
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-0.31619600551803684,
|
| 133 |
+
-2.605601541465191,
|
| 134 |
+
2.2604947632325763
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 2,
|
| 138 |
+
"dist": 2.0417002705160923,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.7417141097395543,
|
| 143 |
+
0.6715388944435241,
|
| 144 |
+
-2.9049746175561775
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.7417141097395548,
|
| 148 |
+
-0.6715388944435241,
|
| 149 |
+
-2.499853937663381
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
596,
|
| 154 |
+
130,
|
| 155 |
+
869,
|
| 156 |
+
496
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
84,
|
| 160 |
+
481,
|
| 161 |
+
432,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 56841,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02044/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02046/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2046,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "65854cf3-25d9-4c26-b102-65b72a2464c2",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "cb5426b6-f114-4edb-bc5f-65b6227f2134#824",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
11.701745986938477,
|
| 13 |
+
-0.5462238192558289,
|
| 14 |
+
0.39045649766921997
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
10.885342597961426,
|
| 19 |
+
1.0861968845129013,
|
| 20 |
+
1.1584131717681885
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9932383845679444,
|
| 41 |
+
-0.05325876907520186,
|
| 42 |
+
0.10315529524680056,
|
| 43 |
+
11.696611334982107
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.11609268461389062,
|
| 47 |
+
-0.45565880344885495,
|
| 48 |
+
0.8825517228008212,
|
| 49 |
+
3.7184523815207577
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8885598226096835,
|
| 54 |
+
0.4587607673328746,
|
| 55 |
+
2.5669879487032166
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
11.696611334982107,
|
| 66 |
+
3.7184523815207577,
|
| 67 |
+
2.5669879487032166
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 1.980169008170555,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.5001976425715853,
|
| 76 |
+
-0.008985389464676988,
|
| 77 |
+
-3.0529871353405293
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.5001976425715853,
|
| 81 |
+
0.008985389464677404,
|
| 82 |
+
-4.76177490024498
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
503,
|
| 87 |
+
391,
|
| 88 |
+
822,
|
| 89 |
+
623
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
0,
|
| 93 |
+
0,
|
| 94 |
+
0,
|
| 95 |
+
0
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 52598,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02046/view_00_front/rgb.png",
|
| 99 |
+
"ok": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.6202356725261319,
|
| 108 |
+
0.35985906659675715,
|
| 109 |
+
-0.6970001167246441,
|
| 110 |
+
8.570099266960742
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.7844155215993986,
|
| 114 |
+
0.28453979305530974,
|
| 115 |
+
-0.5511164991560176,
|
| 116 |
+
-1.8834356147660838
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8885598226096835,
|
| 121 |
+
0.4587607673328745,
|
| 122 |
+
2.5669879487032166
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
8.570099266960742,
|
| 133 |
+
-1.8834356147660838,
|
| 134 |
+
2.5669879487032166
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.980169008170555,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.893429321415601,
|
| 143 |
+
0.42653696690757403,
|
| 144 |
+
-3.8965371842484453
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.8934293214156002,
|
| 148 |
+
-0.4265369669075749,
|
| 149 |
+
-3.9182248513370643
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
235,
|
| 154 |
+
348,
|
| 155 |
+
326,
|
| 156 |
+
537
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
514,
|
| 160 |
+
442,
|
| 161 |
+
894,
|
| 162 |
+
782
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 11612,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02046/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 270,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.11609268461389083,
|
| 175 |
+
-0.45565880344885495,
|
| 176 |
+
0.8825517228008212,
|
| 177 |
+
14.742010141342172
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.9932383845679444,
|
| 181 |
+
0.05325876907520196,
|
| 182 |
+
-0.10315529524680075,
|
| 183 |
+
-0.13308050990362014
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
-0.0,
|
| 187 |
+
0.8885598226096835,
|
| 188 |
+
0.4587607673328746,
|
| 189 |
+
2.5669879487032166
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
14.742010141342172,
|
| 200 |
+
-0.13308050990362014,
|
| 201 |
+
2.5669879487032166
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 2,
|
| 205 |
+
"dist": 1.980169008170555,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.7633022207961482,
|
| 210 |
+
0.5706587773788847,
|
| 211 |
+
-4.175682349801919
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.7633022207961475,
|
| 215 |
+
-0.5706587773788874,
|
| 216 |
+
-3.639079685783585
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
0,
|
| 221 |
+
0,
|
| 222 |
+
0,
|
| 223 |
+
0
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
0,
|
| 227 |
+
0,
|
| 228 |
+
0,
|
| 229 |
+
0
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 0,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02046/view_02_back/rgb.png",
|
| 233 |
+
"ok": false
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": false
|
| 237 |
+
}
|
data/batch_v5/pair_02048/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2048,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "e2271d9f-eaff-4b6c-a785-73d6b2869ee2",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "a714271c-22a0-41f0-a5fc-531042f51bf7#259",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.6138099431991577,
|
| 13 |
+
-6.420754909515381,
|
| 14 |
+
0.3363099992275238
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-2.6666805957044875,
|
| 19 |
+
-5.530651135104043,
|
| 20 |
+
1.0122014922755105
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.6476659794703036,
|
| 41 |
+
0.5972768623894349,
|
| 42 |
+
-0.47306355671411043,
|
| 43 |
+
-3.3290459072744296
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.7619243919423845,
|
| 47 |
+
0.5077090432926513,
|
| 48 |
+
-0.4021228025393343,
|
| 49 |
+
-6.986230756600338
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.6208799215734817,
|
| 54 |
+
0.7839056850073912,
|
| 55 |
+
2.644197342611281
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-3.3290459072744296,
|
| 66 |
+
-6.986230756600338,
|
| 67 |
+
2.644197342611281
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.5354643110482722,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.6800501397471925,
|
| 76 |
+
0.12135295655153877,
|
| 77 |
+
-2.1779934718372402
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.6800501397471899,
|
| 81 |
+
-0.121352956551537,
|
| 82 |
+
-2.847972367002642
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
128,
|
| 87 |
+
220,
|
| 88 |
+
408,
|
| 89 |
+
656
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
504,
|
| 93 |
+
369,
|
| 94 |
+
938,
|
| 95 |
+
791
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 51360,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02048/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.08079289826661805,
|
| 108 |
+
-0.781343027023362,
|
| 109 |
+
0.6188502094300766,
|
| 110 |
+
-0.585085263474586
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.9967309103211759,
|
| 114 |
+
0.0633340122594257,
|
| 115 |
+
-0.05016268833947209,
|
| 116 |
+
-6.101761001298992
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.6208799215734817,
|
| 121 |
+
0.7839056850073912,
|
| 122 |
+
2.644197342611281
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-0.585085263474586,
|
| 133 |
+
-6.101761001298992,
|
| 134 |
+
2.644197342611281
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.5354643110482722,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.401064736916779,
|
| 143 |
+
0.649337221624561,
|
| 144 |
+
-2.5961749385113615
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.40106473691677813,
|
| 148 |
+
-0.6493372216245616,
|
| 149 |
+
-2.4297909003285234
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
436,
|
| 154 |
+
128,
|
| 155 |
+
847,
|
| 156 |
+
504
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
169,
|
| 160 |
+
509,
|
| 161 |
+
539,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 98090,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02048/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.9967309103211759,
|
| 175 |
+
-0.0674815323033315,
|
| 176 |
+
0.04442673978939389,
|
| 177 |
+
-2.0141872904625435
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.08079289826661801,
|
| 181 |
+
-0.8325104132371285,
|
| 182 |
+
0.5480865984873425,
|
| 183 |
+
-4.420543016332475
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.5498842193132478,
|
| 188 |
+
0.8352408906119599,
|
| 189 |
+
3.0441973426112807
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-2.0141872904625435,
|
| 200 |
+
-4.420543016332475,
|
| 201 |
+
3.0441973426112807
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 3,
|
| 205 |
+
"dist": 1.5354643110482722,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.5606713938074177,
|
| 210 |
+
-0.149154635057843,
|
| 211 |
+
-2.334629556811252
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.5606713938074179,
|
| 215 |
+
0.149154635057843,
|
| 216 |
+
-3.340240108928811
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
636,
|
| 221 |
+
310,
|
| 222 |
+
854,
|
| 223 |
+
738
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
0,
|
| 227 |
+
0,
|
| 228 |
+
0,
|
| 229 |
+
0
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 35910,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02048/view_02_back/rgb.png",
|
| 233 |
+
"ok": false
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": false
|
| 237 |
+
}
|
data/batch_v5/pair_02050/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2050,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "7388a66a-0ef2-4c30-9274-24f575fa4931",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "641eaf99-ec77-40a6-bef8-2ff72ef2b1d1#272",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.7875987887382507,
|
| 13 |
+
1.7726645469665527,
|
| 14 |
+
0.24738143384456635
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.1099208444356918,
|
| 19 |
+
2.833591401576996,
|
| 20 |
+
1.0029426217079163
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.288096090704282,
|
| 41 |
+
-0.7443346292731189,
|
| 42 |
+
0.6024670963511277,
|
| 43 |
+
1.0974778896739354
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9576015050744805,
|
| 47 |
+
0.223934377434722,
|
| 48 |
+
-0.18125328157584722,
|
| 49 |
+
1.687513774939858
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.629141760073016,
|
| 54 |
+
0.7772905799842346,
|
| 55 |
+
3.265175570620692
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
1.0974778896739354,
|
| 66 |
+
1.687513774939858,
|
| 67 |
+
3.265175570620692
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 1,
|
| 71 |
+
"dist": 1.3417637672213798,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.4615427142773474,
|
| 76 |
+
0.4764242790501394,
|
| 77 |
+
-3.296027797516679
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.4615427142773467,
|
| 81 |
+
-0.47642427905013895,
|
| 82 |
+
-3.4968334845485107
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
555,
|
| 87 |
+
238,
|
| 88 |
+
711,
|
| 89 |
+
501
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
233,
|
| 93 |
+
480,
|
| 94 |
+
546,
|
| 95 |
+
725
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 20926,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02050/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9576015050744805,
|
| 108 |
+
-0.22393437743472183,
|
| 109 |
+
0.18125328157584714,
|
| 110 |
+
-0.3331456172550553
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.2880960907042818,
|
| 114 |
+
-0.7443346292731188,
|
| 115 |
+
0.6024670963511278,
|
| 116 |
+
4.3493656805326815
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.629141760073016,
|
| 121 |
+
0.7772905799842345,
|
| 122 |
+
3.265175570620692
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-0.3331456172550553,
|
| 133 |
+
4.3493656805326815,
|
| 134 |
+
3.265175570620692
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 4,
|
| 138 |
+
"dist": 1.3417637672213798,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.3071524824955145,
|
| 143 |
+
-0.1210752562805335,
|
| 144 |
+
-2.812409548459327
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.3071524824955145,
|
| 148 |
+
0.12107525628053362,
|
| 149 |
+
-3.980451733605862
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
454,
|
| 154 |
+
405,
|
| 155 |
+
776,
|
| 156 |
+
671
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
338,
|
| 160 |
+
356,
|
| 161 |
+
564,
|
| 162 |
+
563
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 54971,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02050/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02051/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2051,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "7e0d1d3c-c380-41df-acba-b14b4a974f3e",
|
| 6 |
+
"target_category": "pier",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "24caaf37-afd3-4cc9-84b5-f27e9cf84d8a#253",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.26089900732040405,
|
| 13 |
+
1.9098999500274658,
|
| 14 |
+
0.22242200374603271
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.0468105673789978,
|
| 19 |
+
4.231601297855377,
|
| 20 |
+
0.9596220552921295
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.6907249985739087,
|
| 41 |
+
0.5867447421318822,
|
| 42 |
+
-0.42264593210589985,
|
| 43 |
+
-1.5646623477801678
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.723117539785251,
|
| 47 |
+
0.5604611129922962,
|
| 48 |
+
-0.4037132205890248,
|
| 49 |
+
1.7231411461575035
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5844775003402848,
|
| 54 |
+
0.8114099158846731,
|
| 55 |
+
3.2995379691721207
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-1.5646623477801678,
|
| 66 |
+
1.7231411461575035,
|
| 67 |
+
3.2995379691721207
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 11,
|
| 71 |
+
"dist": 2.4453210269046584,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "behind",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.7654933646921012,
|
| 76 |
+
0.9288577156522877,
|
| 77 |
+
-3.5528433819460066
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.7654933646921009,
|
| 81 |
+
-0.9288577156522875,
|
| 82 |
+
-3.123229677131582
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
188,
|
| 87 |
+
143,
|
| 88 |
+
486,
|
| 89 |
+
421
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
608,
|
| 93 |
+
653,
|
| 94 |
+
859,
|
| 95 |
+
909
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 36849,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02051/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.723117539785251,
|
| 108 |
+
-0.5604611129922962,
|
| 109 |
+
0.4037132205890248,
|
| 110 |
+
1.1937546904342171
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.6907249985739087,
|
| 114 |
+
0.5867447421318822,
|
| 115 |
+
-0.42264593210589985,
|
| 116 |
+
1.6599430635109547
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.5844775003402848,
|
| 121 |
+
0.8114099158846731,
|
| 122 |
+
3.2995379691721207
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
1.1937546904342171,
|
| 133 |
+
1.6599430635109547,
|
| 134 |
+
3.2995379691721207
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 2,
|
| 138 |
+
"dist": 2.4453210269046584,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.8792341330771838,
|
| 143 |
+
0.8365673283442896,
|
| 144 |
+
-3.48636446195351
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.8792341330771838,
|
| 148 |
+
-0.8365673283442894,
|
| 149 |
+
-3.189708597124079
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
566,
|
| 154 |
+
160,
|
| 155 |
+
874,
|
| 156 |
+
443
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
138,
|
| 160 |
+
624,
|
| 161 |
+
386,
|
| 162 |
+
875
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 41391,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02051/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02055/meta.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2055,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "88360658-0fdc-4cc5-a058-13e3c48e665d",
|
| 6 |
+
"target_category": "others",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "79c086e6-b5cb-4488-9361-1a70db853c7b#633",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
4.4929423332214355,
|
| 13 |
+
0.4710325598716736,
|
| 14 |
+
0.36999261379241943
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
2.9647436141967773,
|
| 19 |
+
1.4716581106185913,
|
| 20 |
+
1.2550000846385956
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.205121711630429,
|
| 41 |
+
-0.7434571203320376,
|
| 42 |
+
0.6365505428835933,
|
| 43 |
+
6.54004860827664
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9787364729168945,
|
| 47 |
+
-0.15581231645720658,
|
| 48 |
+
0.13340704112765633,
|
| 49 |
+
1.5605124169510596
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.6503799137948784,
|
| 54 |
+
0.7596090887635341,
|
| 55 |
+
4.167166884452587
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
6.54004860827664,
|
| 66 |
+
1.5605124169510596,
|
| 67 |
+
4.167166884452587
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 1,
|
| 71 |
+
"dist": 2.0297490093826194,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "behind",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.6464077296031652,
|
| 76 |
+
0.7779157582848963,
|
| 77 |
+
-4.4998244941893475
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.6464077296031652,
|
| 81 |
+
-0.7779157582848986,
|
| 82 |
+
-4.332798982440451
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
552,
|
| 87 |
+
257,
|
| 88 |
+
707,
|
| 89 |
+
485
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
167,
|
| 93 |
+
520,
|
| 94 |
+
601,
|
| 95 |
+
669
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 12766,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02055/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9787364729168945,
|
| 108 |
+
0.15581231645720658,
|
| 109 |
+
-0.13340704112765633,
|
| 110 |
+
3.1396758920031793
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.205121711630429,
|
| 114 |
+
-0.7434571203320376,
|
| 115 |
+
0.6365505428835933,
|
| 116 |
+
3.7825509698126663
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.6503799137948784,
|
| 121 |
+
0.7596090887635341,
|
| 122 |
+
4.167166884452587
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
3.1396758920031793,
|
| 133 |
+
3.7825509698126663,
|
| 134 |
+
4.167166884452587
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 4,
|
| 138 |
+
"dist": 2.0297490093826194,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.645226899251981,
|
| 143 |
+
-0.2032216451551862,
|
| 144 |
+
-3.6597712756200567
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.6452268992519814,
|
| 148 |
+
0.20322164515518465,
|
| 149 |
+
-5.17285220100974
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
561,
|
| 154 |
+
459,
|
| 155 |
+
748,
|
| 156 |
+
698
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
290,
|
| 160 |
+
312,
|
| 161 |
+
513,
|
| 162 |
+
498
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 10340,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02055/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.20512171163042878,
|
| 175 |
+
0.7434571203320377,
|
| 176 |
+
-0.6365505428835933,
|
| 177 |
+
0.9176373391415726
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.9787364729168947,
|
| 181 |
+
0.15581231645720642,
|
| 182 |
+
-0.13340704112765617,
|
| 183 |
+
0.3821782535392061
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.6503799137948784,
|
| 188 |
+
0.7596090887635341,
|
| 189 |
+
4.167166884452587
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
0.9176373391415726,
|
| 200 |
+
0.3821782535392061,
|
| 201 |
+
4.167166884452587
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 8,
|
| 205 |
+
"dist": 2.0297490093826194,
|
| 206 |
+
"lr": "left",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
-0.6464077296031651,
|
| 210 |
+
-0.20232467568813828,
|
| 211 |
+
-3.660539263962066
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
0.6464077296031648,
|
| 215 |
+
0.20232467568813872,
|
| 216 |
+
-5.17208421266773
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
280,
|
| 221 |
+
453,
|
| 222 |
+
462,
|
| 223 |
+
710
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
432,
|
| 227 |
+
355,
|
| 228 |
+
814,
|
| 229 |
+
579
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 20656,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02055/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"view_idx": 3,
|
| 237 |
+
"view_label": "left",
|
| 238 |
+
"azimuth_offset_deg": 270,
|
| 239 |
+
"cam2world": [
|
| 240 |
+
[
|
| 241 |
+
0.9787364729168945,
|
| 242 |
+
-0.15581231645720658,
|
| 243 |
+
0.13340704112765633,
|
| 244 |
+
4.318010055415034
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
0.205121711630429,
|
| 248 |
+
0.7434571203320376,
|
| 249 |
+
-0.6365505428835933,
|
| 250 |
+
-1.8398602993224014
|
| 251 |
+
],
|
| 252 |
+
[
|
| 253 |
+
-0.0,
|
| 254 |
+
0.6503799137948784,
|
| 255 |
+
0.7596090887635341,
|
| 256 |
+
4.167166884452587
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
0.0,
|
| 260 |
+
0.0,
|
| 261 |
+
0.0,
|
| 262 |
+
1.0
|
| 263 |
+
]
|
| 264 |
+
],
|
| 265 |
+
"cam_pos_world": [
|
| 266 |
+
4.318010055415034,
|
| 267 |
+
-1.8398602993224014,
|
| 268 |
+
4.167166884452587
|
| 269 |
+
],
|
| 270 |
+
"gt": {
|
| 271 |
+
"clock": 11,
|
| 272 |
+
"dist": 2.0297490093826194,
|
| 273 |
+
"lr": "left",
|
| 274 |
+
"fb": "behind",
|
| 275 |
+
"target_cam_xyz": [
|
| 276 |
+
-0.6452268992519814,
|
| 277 |
+
0.7788127277519443,
|
| 278 |
+
-4.500592482531356
|
| 279 |
+
],
|
| 280 |
+
"anchor_cam_xyz": [
|
| 281 |
+
0.645226899251981,
|
| 282 |
+
-0.7788127277519454,
|
| 283 |
+
-4.3320309940984405
|
| 284 |
+
]
|
| 285 |
+
},
|
| 286 |
+
"target_bbox": [
|
| 287 |
+
322,
|
| 288 |
+
283,
|
| 289 |
+
469,
|
| 290 |
+
486
|
| 291 |
+
],
|
| 292 |
+
"anchor_bbox": [
|
| 293 |
+
541,
|
| 294 |
+
460,
|
| 295 |
+
761,
|
| 296 |
+
720
|
| 297 |
+
],
|
| 298 |
+
"target_pixels": 12407,
|
| 299 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02055/view_03_left/rgb.png",
|
| 300 |
+
"ok": true
|
| 301 |
+
}
|
| 302 |
+
],
|
| 303 |
+
"all_views_ok": true
|
| 304 |
+
}
|
data/batch_v5/pair_02056/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2056,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "4f3e6181-1575-41e5-9a9c-50555c7084fd",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "f99aaaf1-15a8-4efb-9943-9a74c3d9c25e#357",
|
| 9 |
+
"category": "Bed",
|
| 10 |
+
"raw_cat": "front3d_cat17",
|
| 11 |
+
"center": [
|
| 12 |
+
-6.023183345794678,
|
| 13 |
+
-1.7872800827026367,
|
| 14 |
+
0.24928052723407745
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-5.269869804382324,
|
| 19 |
+
-1.3200591802597046,
|
| 20 |
+
0.9544757008552551
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9273225600477126,
|
| 41 |
+
-0.2615998955815084,
|
| 42 |
+
0.26765344058745116,
|
| 43 |
+
-5.063721198411418
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.3742631021441418,
|
| 47 |
+
-0.6481736604251994,
|
| 48 |
+
0.6631727047341757,
|
| 49 |
+
-0.10963581993642935
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.7151478172816739,
|
| 54 |
+
0.6989732465819116,
|
| 55 |
+
2.123866269202623
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-5.063721198411418,
|
| 66 |
+
-0.10963581993642935,
|
| 67 |
+
2.123866269202623
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.132729842572099,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.2618505487031175,
|
| 76 |
+
0.0022058814177743358,
|
| 77 |
+
-1.6752688394794621
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.2618505487031175,
|
| 81 |
+
-0.0022058814177734476,
|
| 82 |
+
-2.679656510240907
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
224,
|
| 87 |
+
173,
|
| 88 |
+
527,
|
| 89 |
+
856
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
420,
|
| 93 |
+
291,
|
| 94 |
+
973,
|
| 95 |
+
889
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 97524,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02056/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.3742631021441418,
|
| 108 |
+
0.6481736604251993,
|
| 109 |
+
-0.6631727047341757,
|
| 110 |
+
-7.090560386633243
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.9273225600477126,
|
| 114 |
+
-0.26159989558150837,
|
| 115 |
+
0.26765344058745116,
|
| 116 |
+
-0.9708642548040877
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7151478172816739,
|
| 121 |
+
0.6989732465819115,
|
| 122 |
+
2.123866269202623
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-7.090560386633243,
|
| 133 |
+
-0.9708642548040877,
|
| 134 |
+
2.123866269202623
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 11,
|
| 138 |
+
"dist": 1.132729842572099,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.35760097312868,
|
| 143 |
+
0.4351859227326509,
|
| 144 |
+
-2.1182682432292834
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.3576009731286791,
|
| 148 |
+
-0.4351859227326509,
|
| 149 |
+
-2.2366571064910867
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
75,
|
| 154 |
+
93,
|
| 155 |
+
562,
|
| 156 |
+
543
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
262,
|
| 160 |
+
445,
|
| 161 |
+
1023,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 152354,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02056/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02062/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2062,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "61476ed6-15be-4931-b3d8-5ac274b2e0a3",
|
| 6 |
+
"target_category": "others",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "154620a2-e63e-474b-b950-b7cc287b0e43#408",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
1.9282920360565186,
|
| 13 |
+
-2.109870433807373,
|
| 14 |
+
0.37505200505256653
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
2.6583502292633057,
|
| 19 |
+
-0.7980530112981796,
|
| 20 |
+
1.213623970746994
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.18615433942371087,
|
| 41 |
+
0.7542039892871595,
|
| 42 |
+
-0.6297006467021103,
|
| 43 |
+
0.23776304659035352
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9825205147546395,
|
| 47 |
+
-0.14289609561133665,
|
| 48 |
+
0.11930693167336878,
|
| 49 |
+
-1.0645031291564808
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.6409033065934127,
|
| 54 |
+
0.7676216200691783,
|
| 55 |
+
3.300117260064733
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
0.23776304659035352,
|
| 66 |
+
-1.0645031291564808,
|
| 67 |
+
3.300117260064733
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 10,
|
| 71 |
+
"dist": 1.7196083441050285,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.7123955149625569,
|
| 76 |
+
0.45030137976347007,
|
| 77 |
+
-3.0940933273318683
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.7123955149625578,
|
| 81 |
+
-0.45030137976347007,
|
| 82 |
+
-3.4345900933855713
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
126,
|
| 87 |
+
271,
|
| 88 |
+
465,
|
| 89 |
+
485
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
516,
|
| 93 |
+
355,
|
| 94 |
+
1007,
|
| 95 |
+
983
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 34800,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02062/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9825205147546393,
|
| 108 |
+
0.142896095611337,
|
| 109 |
+
-0.11930693167336907,
|
| 110 |
+
1.9038625392636157
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.18615433942371132,
|
| 114 |
+
0.7542039892871594,
|
| 115 |
+
-0.6297006467021103,
|
| 116 |
+
-3.5095198086223345
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.6409033065934127,
|
| 121 |
+
0.7676216200691784,
|
| 122 |
+
3.300117260064733
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
1.9038625392636157,
|
| 133 |
+
-3.5095198086223345,
|
| 134 |
+
3.300117260064733
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.7196083441050285,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.23654832302932993,
|
| 143 |
+
0.8155719721406236,
|
| 144 |
+
-3.3990653660750625
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.23654832302932993,
|
| 148 |
+
-0.8155719721406225,
|
| 149 |
+
-3.1296180546423744
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
465,
|
| 154 |
+
126,
|
| 155 |
+
655,
|
| 156 |
+
477
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
59,
|
| 160 |
+
523,
|
| 161 |
+
823,
|
| 162 |
+
971
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 37914,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02062/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02073/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2073,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "8225d304-2d16-419c-b9e7-9634a68e2f42",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "b4605349-5ca9-44ec-bb78-1edf5fac49b5#389",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.7198407649993896,
|
| 13 |
+
2.7517738342285156,
|
| 14 |
+
0.5399245023727417
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-2.3517284393310547,
|
| 19 |
+
2.0654506385326385,
|
| 20 |
+
1.0944465696811676
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 45,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.04249261010567001,
|
| 41 |
+
-0.46741590852776443,
|
| 42 |
+
0.8830157113786663,
|
| 43 |
+
0.3741377006723705
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9990967811410502,
|
| 47 |
+
-0.019879677658028387,
|
| 48 |
+
0.03755556323376573,
|
| 49 |
+
2.511108701920665
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8838139888411913,
|
| 54 |
+
0.467838469055958,
|
| 55 |
+
2.0940080729023585
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
0.3741377006723705,
|
| 66 |
+
2.511108701920665,
|
| 67 |
+
2.0940080729023585
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 11,
|
| 71 |
+
"dist": 1.0852724473856747,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "behind",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.32942636953311766,
|
| 76 |
+
0.39954629774660844,
|
| 77 |
+
-2.891352891712624
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.3294263695331181,
|
| 81 |
+
-0.3995462977466082,
|
| 82 |
+
-2.5670376483038
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
238,
|
| 87 |
+
291,
|
| 88 |
+
573,
|
| 89 |
+
501
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
491,
|
| 93 |
+
496,
|
| 94 |
+
764,
|
| 95 |
+
833
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 46310,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02073/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9990967811410502,
|
| 108 |
+
0.02425470502677607,
|
| 109 |
+
-0.034890273682741044,
|
| 110 |
+
-2.13828106770531
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.04249261010567,
|
| 114 |
+
-0.5702826364282131,
|
| 115 |
+
0.8203487628288922,
|
| 116 |
+
4.81853453921817
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8210903871514699,
|
| 121 |
+
0.5707981921199904,
|
| 122 |
+
2.4940080729023584
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-2.13828106770531,
|
| 133 |
+
4.81853453921817,
|
| 134 |
+
2.4940080729023584
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.0852724473856747,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.3302403027143268,
|
| 143 |
+
0.41569234563130975,
|
| 144 |
+
-3.049908910478024
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.33024030271432636,
|
| 148 |
+
-0.41569234563130997,
|
| 149 |
+
-2.8254514533926107
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
505,
|
| 154 |
+
271,
|
| 155 |
+
734,
|
| 156 |
+
534
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
295,
|
| 160 |
+
501,
|
| 161 |
+
538,
|
| 162 |
+
809
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 34994,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02073/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02077/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2077,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "7f985ce5-b4a3-4e90-815a-a6b69952d9f9",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "70e4c0ab-9ca2-4542-96fd-9355e048db91#327",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.30586767196655273,
|
| 13 |
+
-1.144088625907898,
|
| 14 |
+
0.17934571206569672
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.4828607439994812,
|
| 19 |
+
0.49431440234184265,
|
| 20 |
+
0.8737020194530487
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9660493796160179,
|
| 41 |
+
0.16066327590439375,
|
| 42 |
+
-0.202326241301458,
|
| 43 |
+
-1.162002993728756
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.2583574967820891,
|
| 47 |
+
-0.6007515165910863,
|
| 48 |
+
0.7565375200014886,
|
| 49 |
+
2.5454649468001436
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.7831251030896523,
|
| 54 |
+
0.6218641916936699,
|
| 55 |
+
2.8859166461512467
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-1.162002993728756,
|
| 66 |
+
2.5454649468001436,
|
| 67 |
+
2.8859166461512467
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 7,
|
| 71 |
+
"dist": 1.788245428383412,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.12615482883252643,
|
| 76 |
+
-0.23447076798499,
|
| 77 |
+
-2.9405048670967817
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.12615482883252732,
|
| 81 |
+
0.23447076798499233,
|
| 82 |
+
-4.647623897693427
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
372,
|
| 87 |
+
395,
|
| 88 |
+
554,
|
| 89 |
+
770
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
553,
|
| 93 |
+
412,
|
| 94 |
+
588,
|
| 95 |
+
488
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 45153,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02077/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.8657864052325404,
|
| 108 |
+
0.3111893793100178,
|
| 109 |
+
-0.39188655337885925,
|
| 110 |
+
-1.8812070220973245
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.5004137293425468,
|
| 114 |
+
0.5384015630693019,
|
| 115 |
+
-0.6780190678513526,
|
| 116 |
+
-2.8973351077025735
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7831251030896524,
|
| 121 |
+
0.6218641916936699,
|
| 122 |
+
2.8859166461512467
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-1.8812070220973245,
|
| 133 |
+
-2.8973351077025735,
|
| 134 |
+
2.8859166461512467
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 11,
|
| 138 |
+
"dist": 1.788245428383412,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.48655878255951335,
|
| 143 |
+
0.6854041209613533,
|
| 144 |
+
-4.098920364978586
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.48655878255951435,
|
| 148 |
+
-0.6854041209613543,
|
| 149 |
+
-3.489208399811621
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
353,
|
| 154 |
+
227,
|
| 155 |
+
454,
|
| 156 |
+
499
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
571,
|
| 160 |
+
607,
|
| 161 |
+
690,
|
| 162 |
+
770
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 18234,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02077/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02088/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2088,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "7e259fdb-ecdc-4498-bdd3-b95c1218fb89",
|
| 6 |
+
"target_category": "lighting",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "ce61bf54-e4cd-4304-9b2a-98478a4a4171#301",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
1.0095813274383545,
|
| 13 |
+
-0.37155681848526,
|
| 14 |
+
0.36833590269088745
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
2.46305513381958,
|
| 19 |
+
-0.5530126830562949,
|
| 20 |
+
1.112774670124054
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.05067656870527588,
|
| 41 |
+
0.8695540392525369,
|
| 42 |
+
-0.4912307586092881,
|
| 43 |
+
0.40599299974082426
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9987151172302637,
|
| 47 |
+
0.04412270751977762,
|
| 48 |
+
-0.024925916169013837,
|
| 49 |
+
-0.5297878022419824
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.4918627445748675,
|
| 54 |
+
0.8706727516692356,
|
| 55 |
+
3.0984653095329855
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
0.40599299974082426,
|
| 66 |
+
-0.5297878022419824,
|
| 67 |
+
3.0984653095329855
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 12,
|
| 71 |
+
"dist": 1.6430768135059792,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "behind",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.12743989013378865,
|
| 76 |
+
0.8110146952819739,
|
| 77 |
+
-2.738800024175754
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.12743989013378842,
|
| 81 |
+
-0.8110146952819739,
|
| 82 |
+
-2.6774944874073383
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
458,
|
| 87 |
+
137,
|
| 88 |
+
700,
|
| 89 |
+
395
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
0,
|
| 93 |
+
559,
|
| 94 |
+
976,
|
| 95 |
+
988
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 17029,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02088/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 270,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9987151172302638,
|
| 108 |
+
0.04412270751977748,
|
| 109 |
+
-0.024925916169013754,
|
| 110 |
+
1.6688151791577626
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.05067656870527572,
|
| 114 |
+
-0.869554039252537,
|
| 115 |
+
0.4912307586092881,
|
| 116 |
+
0.8680404801173656
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.49186274457486756,
|
| 121 |
+
0.8706727516692356,
|
| 122 |
+
3.0984653095329855
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
1.6688151791577626,
|
| 133 |
+
0.8680404801173656,
|
| 134 |
+
3.0984653095329855
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.6430768135059792,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.7212053511716174,
|
| 143 |
+
0.29403928747401487,
|
| 144 |
+
-2.446748914875926
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.7212053511716169,
|
| 148 |
+
-0.2940392874740151,
|
| 149 |
+
-2.969545596707166
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
195,
|
| 154 |
+
298,
|
| 155 |
+
380,
|
| 156 |
+
554
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
580,
|
| 160 |
+
242,
|
| 161 |
+
1014,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 13468,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02088/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02089/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2089,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "9ae7ae8d-8b27-4cbc-b57b-3c0b3cffb9e5",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "c2091907-53cb-4a8a-b017-343255e04b0a#187",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-2.4793758392333984,
|
| 13 |
+
2.340989351272583,
|
| 14 |
+
0.5814054608345032
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.8570603132247925,
|
| 19 |
+
2.7993061542510986,
|
| 20 |
+
1.531758189201355
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.09307407335403778,
|
| 41 |
+
-0.6709927737313283,
|
| 42 |
+
0.7355990174474308,
|
| 43 |
+
-0.708108240987416
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9956591871063548,
|
| 47 |
+
0.06272430511468569,
|
| 48 |
+
-0.06876368720911219,
|
| 49 |
+
2.4336569016050387
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.7388060362153374,
|
| 54 |
+
0.6739181262228978,
|
| 55 |
+
2.3942596371229694
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-0.708108240987416,
|
| 66 |
+
2.4336569016050387,
|
| 67 |
+
2.3942596371229694
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 2,
|
| 71 |
+
"dist": 1.224949474108273,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.2571243882039269,
|
| 76 |
+
0.1566523571538858,
|
| 77 |
+
-1.4515667659170735
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.2571243882039269,
|
| 81 |
+
-0.1566523571538858,
|
| 82 |
+
-2.5182858320603976
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
554,
|
| 87 |
+
0,
|
| 88 |
+
881,
|
| 89 |
+
854
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
156,
|
| 93 |
+
312,
|
| 94 |
+
680,
|
| 95 |
+
999
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 172846,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02089/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.7698506713748833,
|
| 108 |
+
0.43011075894078454,
|
| 109 |
+
-0.4715237839462859,
|
| 110 |
+
-3.104158035582761
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.6382240545322946,
|
| 114 |
+
-0.5188163219244012,
|
| 115 |
+
0.5687703229961938,
|
| 116 |
+
3.699114924961304
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7388060362153372,
|
| 121 |
+
0.6739181262228978,
|
| 122 |
+
2.3942596371229694
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-3.104158035582761,
|
| 133 |
+
3.699114924961304,
|
| 134 |
+
2.3942596371229694
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.224949474108273,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.3857994168809831,
|
| 143 |
+
0.3660043487229383,
|
| 144 |
+
-1.6810761217965462
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.38579941688098296,
|
| 148 |
+
-0.36600434872293786,
|
| 149 |
+
-2.2887764761809257
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
87,
|
| 154 |
+
16,
|
| 155 |
+
556,
|
| 156 |
+
633
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
264,
|
| 160 |
+
347,
|
| 161 |
+
1023,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 196664,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02089/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.6382240545322946,
|
| 175 |
+
0.5883385979225615,
|
| 176 |
+
-0.4965156094332514,
|
| 177 |
+
-3.2971852484285584
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.7698506713748833,
|
| 181 |
+
0.48774633752463753,
|
| 182 |
+
-0.4116229512733027,
|
| 183 |
+
1.6342077934081751
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.6449505441704944,
|
| 188 |
+
0.7642243097246928,
|
| 189 |
+
2.7942596371229693
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-3.2971852484285584,
|
| 200 |
+
1.6342077934081751,
|
| 201 |
+
2.7942596371229693
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 12,
|
| 205 |
+
"dist": 1.224949474108273,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.022170619866105135,
|
| 210 |
+
0.6013025477151154,
|
| 211 |
+
-2.1594600332408924
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.022170619866105135,
|
| 215 |
+
-0.6013025477151164,
|
| 216 |
+
-2.388099603355929
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
323,
|
| 221 |
+
42,
|
| 222 |
+
659,
|
| 223 |
+
535
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
77,
|
| 227 |
+
437,
|
| 228 |
+
851,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 107029,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02089/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_02092/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2092,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "e735842a-ced4-40b9-be96-64dcca49afa6",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "e89afe87-760f-4291-bc6f-8554c65dd30c#425",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.0962004661560059,
|
| 13 |
+
3.9618465900421143,
|
| 14 |
+
0.22537900507450104
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.08293131366372108,
|
| 19 |
+
4.518355846405029,
|
| 20 |
+
0.5970358848571777
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.866156340351322,
|
| 41 |
+
-0.21208270118577646,
|
| 42 |
+
0.4525418454982362,
|
| 43 |
+
0.24364931544810142
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.4997731426049271,
|
| 47 |
+
-0.3675603201753245,
|
| 48 |
+
0.7842998259361073,
|
| 49 |
+
5.68414566854417
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.9054945272558844,
|
| 54 |
+
0.42435793984517645,
|
| 55 |
+
1.1925307447020175
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
0.24364931544810142,
|
| 66 |
+
5.68414566854417,
|
| 67 |
+
1.1925307447020175
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 1.2143087597888078,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.2997605604861886,
|
| 76 |
+
-0.04145715433893016,
|
| 77 |
+
-1.3148231270962007
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.29976056048618904,
|
| 81 |
+
0.04145715433892927,
|
| 82 |
+
-2.3675554800826233
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
119,
|
| 87 |
+
362,
|
| 88 |
+
399,
|
| 89 |
+
873
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
332,
|
| 93 |
+
333,
|
| 94 |
+
1023,
|
| 95 |
+
795
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 90683,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02092/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.4997731426049269,
|
| 108 |
+
0.36756032017532453,
|
| 109 |
+
-0.7842998259361073,
|
| 110 |
+
-2.033610340230462
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.866156340351322,
|
| 114 |
+
-0.21208270118577638,
|
| 115 |
+
0.452541845498236,
|
| 116 |
+
5.073316423581536
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.9054945272558842,
|
| 121 |
+
0.4243579398451765,
|
| 122 |
+
1.1925307447020175
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-2.033610340230462,
|
| 133 |
+
5.073316423581536,
|
| 134 |
+
1.1925307447020175
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.2143087597888078,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.4942143647543187,
|
| 143 |
+
0.2954724092248604,
|
| 144 |
+
-2.0337630766798815
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.49421436475432,
|
| 148 |
+
-0.29547240922486073,
|
| 149 |
+
-1.648615530498943
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
45,
|
| 154 |
+
312,
|
| 155 |
+
515,
|
| 156 |
+
459
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
314,
|
| 160 |
+
405,
|
| 161 |
+
1023,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 43793,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02092/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02104/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2104,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "4e9dccf1-ff60-4f7f-96bf-0af893fb1cc0",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "df76627b-4746-482a-abe3-b9a6f5388e7a#270",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-2.2418999671936035,
|
| 13 |
+
-1.7975000143051147,
|
| 14 |
+
0.4073590040206909
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-3.448662042617798,
|
| 19 |
+
-2.03945329785347,
|
| 20 |
+
1.3297180831432343
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.794211495864236,
|
| 41 |
+
-0.4109000574203276,
|
| 42 |
+
0.44764857047584106,
|
| 43 |
+
-1.809026729508648
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.6076414237336791,
|
| 47 |
+
0.5370627092031992,
|
| 48 |
+
-0.5850944765986321,
|
| 49 |
+
-3.2729021873437887
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
-0.0,
|
| 53 |
+
0.7366985741775881,
|
| 54 |
+
0.6762212735523104,
|
| 55 |
+
2.4339119906325197
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-1.809026729508648,
|
| 66 |
+
-3.2729021873437887,
|
| 67 |
+
2.4339119906325197
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 10,
|
| 71 |
+
"dist": 1.5380384809690966,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.5527225753836196,
|
| 76 |
+
0.5227075692953582,
|
| 77 |
+
-2.2023439467936283
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.5527225753836205,
|
| 81 |
+
-0.5227075692953584,
|
| 82 |
+
-2.4274229897813564
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
105,
|
| 87 |
+
44,
|
| 88 |
+
401,
|
| 89 |
+
536
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
530,
|
| 93 |
+
474,
|
| 94 |
+
912,
|
| 95 |
+
949
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 99452,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02104/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.6076414237336791,
|
| 108 |
+
-0.5370627092031992,
|
| 109 |
+
0.5850944765986321,
|
| 110 |
+
-1.4908554736412043
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.794211495864236,
|
| 114 |
+
-0.4109000574203276,
|
| 115 |
+
0.44764857047584106,
|
| 116 |
+
-0.8822223806822396
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7366985741775881,
|
| 121 |
+
0.6762212735523104,
|
| 122 |
+
2.4339119906325197
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-1.4908554736412043,
|
| 133 |
+
-0.8822223806822396,
|
| 134 |
+
2.4339119906325197
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 1,
|
| 138 |
+
"dist": 1.5380384809690966,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.27055827318118264,
|
| 143 |
+
0.7135130730816908,
|
| 144 |
+
-2.4102139859099774
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.27055827318118164,
|
| 148 |
+
-0.7135130730816899,
|
| 149 |
+
-2.2195529506650056
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
488,
|
| 154 |
+
24,
|
| 155 |
+
767,
|
| 156 |
+
441
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
186,
|
| 160 |
+
541,
|
| 161 |
+
610,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 94057,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02104/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": true
|
| 170 |
+
}
|
data/batch_v5/pair_02116/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2116,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "0cc3d697-b060-4620-bd4f-f85cea2674e6",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "d2a39d7a-6114-48dc-9141-4a7a5fa8dc51#992",
|
| 9 |
+
"category": "Bed",
|
| 10 |
+
"raw_cat": "front3d_cat17",
|
| 11 |
+
"center": [
|
| 12 |
+
2.9535701274871826,
|
| 13 |
+
3.0686841011047363,
|
| 14 |
+
0.3883081078529358
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
2.0110107362270355,
|
| 19 |
+
3.4825337529182434,
|
| 20 |
+
1.2065698206424713
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 45,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.8516998745288611,
|
| 41 |
+
-0.4228367354685429,
|
| 42 |
+
0.30954227314831745,
|
| 43 |
+
3.7163274543063745
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.5240298882005893,
|
| 47 |
+
-0.687231783250691,
|
| 48 |
+
0.5030955698101037,
|
| 49 |
+
5.281275399191209
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5906958364745603,
|
| 54 |
+
0.8068943107815418,
|
| 55 |
+
4.014245000400955
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
3.7163274543063745,
|
| 66 |
+
5.281275399191209,
|
| 67 |
+
4.014245000400955
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 2,
|
| 71 |
+
"dist": 1.3150064528268006,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.5098236510219762,
|
| 76 |
+
0.2987409443317537,
|
| 77 |
+
-3.698303695894631
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.5098236510219758,
|
| 81 |
+
-0.298740944331751,
|
| 82 |
+
-4.274998366521736
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
506,
|
| 87 |
+
302,
|
| 88 |
+
786,
|
| 89 |
+
529
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
81,
|
| 93 |
+
356,
|
| 94 |
+
620,
|
| 95 |
+
819
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 42674,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02116/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 180,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.23169766932402414,
|
| 108 |
+
0.7849369771680764,
|
| 109 |
+
-0.5746217294047082,
|
| 110 |
+
0.19147412177119882
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.9727878443061545,
|
| 114 |
+
0.18695553119889807,
|
| 115 |
+
-0.1368628485905605,
|
| 116 |
+
2.7299845105438423
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.5906958364745603,
|
| 121 |
+
0.806894310781542,
|
| 122 |
+
4.014245000400955
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
0.19147412177119882,
|
| 133 |
+
2.7299845105438423,
|
| 134 |
+
4.014245000400955
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 8,
|
| 138 |
+
"dist": 1.3150064528268006,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.3104883624044805,
|
| 143 |
+
-0.0895672254972637,
|
| 144 |
+
-3.414038438199493
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.3104883624044805,
|
| 148 |
+
0.08956722549726459,
|
| 149 |
+
-4.559263624216875
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
0,
|
| 154 |
+
0,
|
| 155 |
+
0,
|
| 156 |
+
0
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
0,
|
| 160 |
+
0,
|
| 161 |
+
0,
|
| 162 |
+
0
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 0,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02116/view_01_right/rgb.png",
|
| 166 |
+
"ok": false
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": false
|
| 170 |
+
}
|
data/batch_v5/pair_02131/meta.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2131,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "a8c34fc0-a9b7-46a7-9f77-a3e5ed3bba12",
|
| 6 |
+
"target_category": "chair",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "1167a82b-ace6-4cec-a2af-7c6f227a371a#369",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-8.480385780334473,
|
| 13 |
+
6.260348320007324,
|
| 14 |
+
0.17679500579833984
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-9.51092529296875,
|
| 19 |
+
6.05394172668457,
|
| 20 |
+
0.8594286739826202
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.5907683287379032,
|
| 41 |
+
0.5448338250116395,
|
| 42 |
+
-0.595104095838208,
|
| 43 |
+
-10.56285314355557
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.8068412370226404,
|
| 47 |
+
-0.39892676957086853,
|
| 48 |
+
0.4357346104678012,
|
| 49 |
+
7.304645508632513
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.7375727324426639,
|
| 54 |
+
0.6752676982923607,
|
| 55 |
+
2.296419077538946
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-10.56285314355557,
|
| 66 |
+
7.304645508632513,
|
| 67 |
+
2.296419077538946
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 1.253237445102214,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.3876737283317438,
|
| 76 |
+
0.012180155449120988,
|
| 77 |
+
-2.141334699925883
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.3876737283317419,
|
| 81 |
+
-0.012180155449128094,
|
| 82 |
+
-3.125634954169846
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
491,
|
| 87 |
+
261,
|
| 88 |
+
964,
|
| 89 |
+
782
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
216,
|
| 93 |
+
378,
|
| 94 |
+
503,
|
| 95 |
+
667
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 179910,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02131/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.806841237022641,
|
| 108 |
+
0.39892676957086826,
|
| 109 |
+
-0.4357346104678006,
|
| 110 |
+
-10.143156021938175
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.5907683287379026,
|
| 114 |
+
0.5448338250116399,
|
| 115 |
+
-0.5951040958382081,
|
| 116 |
+
4.589947416441989
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.7375727324426637,
|
| 121 |
+
0.6752676982923608,
|
| 122 |
+
2.296419077538946
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-10.143156021938175,
|
| 133 |
+
4.589947416441989,
|
| 134 |
+
2.296419077538946
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 9,
|
| 138 |
+
"dist": 1.253237445102214,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.3547716484983905,
|
| 143 |
+
-0.010037556268974651,
|
| 144 |
+
-2.1170670230001507
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.35477164849839227,
|
| 148 |
+
0.010037556268974096,
|
| 149 |
+
-3.149902631095577
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
51,
|
| 154 |
+
308,
|
| 155 |
+
596,
|
| 156 |
+
794
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
572,
|
| 160 |
+
373,
|
| 161 |
+
795,
|
| 162 |
+
659
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 170044,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02131/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.5907683287379029,
|
| 175 |
+
-0.5448338250116396,
|
| 176 |
+
0.595104095838208,
|
| 177 |
+
-7.428457929747653
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.8068412370226407,
|
| 181 |
+
0.3989267695708683,
|
| 182 |
+
-0.4357346104678009,
|
| 183 |
+
5.009644538059383
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
-0.0,
|
| 187 |
+
0.7375727324426637,
|
| 188 |
+
0.6752676982923607,
|
| 189 |
+
2.296419077538946
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-7.428457929747653,
|
| 200 |
+
5.009644538059383,
|
| 201 |
+
2.296419077538946
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 11,
|
| 205 |
+
"dist": 1.253237445102214,
|
| 206 |
+
"lr": "left",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
-0.3876737283317424,
|
| 210 |
+
0.49131182445091426,
|
| 211 |
+
-2.664674488278175
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
0.3876737283317424,
|
| 215 |
+
-0.49131182445091515,
|
| 216 |
+
-2.6022951658175506
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
182,
|
| 221 |
+
150,
|
| 222 |
+
533,
|
| 223 |
+
569
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
436,
|
| 227 |
+
499,
|
| 228 |
+
873,
|
| 229 |
+
895
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 104513,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02131/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"view_idx": 3,
|
| 237 |
+
"view_label": "left",
|
| 238 |
+
"azimuth_offset_deg": 270,
|
| 239 |
+
"cam2world": [
|
| 240 |
+
[
|
| 241 |
+
-0.8068412370226407,
|
| 242 |
+
-0.3989267695708683,
|
| 243 |
+
0.4357346104678009,
|
| 244 |
+
-7.848155051365047
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
0.5907683287379029,
|
| 248 |
+
-0.5448338250116396,
|
| 249 |
+
0.595104095838208,
|
| 250 |
+
7.724342630249906
|
| 251 |
+
],
|
| 252 |
+
[
|
| 253 |
+
0.0,
|
| 254 |
+
0.7375727324426637,
|
| 255 |
+
0.6752676982923607,
|
| 256 |
+
2.296419077538946
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
0.0,
|
| 260 |
+
0.0,
|
| 261 |
+
0.0,
|
| 262 |
+
1.0
|
| 263 |
+
]
|
| 264 |
+
],
|
| 265 |
+
"cam_pos_world": [
|
| 266 |
+
-7.848155051365047,
|
| 267 |
+
7.724342630249906,
|
| 268 |
+
2.296419077538946
|
| 269 |
+
],
|
| 270 |
+
"gt": {
|
| 271 |
+
"clock": 1,
|
| 272 |
+
"dist": 1.253237445102214,
|
| 273 |
+
"lr": "right",
|
| 274 |
+
"fb": "behind",
|
| 275 |
+
"target_cam_xyz": [
|
| 276 |
+
0.35477164849839227,
|
| 277 |
+
0.513529536169014,
|
| 278 |
+
-2.688942165203907
|
| 279 |
+
],
|
| 280 |
+
"anchor_cam_xyz": [
|
| 281 |
+
-0.3547716484983905,
|
| 282 |
+
-0.5135295361690123,
|
| 283 |
+
-2.5780274888918204
|
| 284 |
+
]
|
| 285 |
+
},
|
| 286 |
+
"target_bbox": [
|
| 287 |
+
459,
|
| 288 |
+
145,
|
| 289 |
+
856,
|
| 290 |
+
561
|
| 291 |
+
],
|
| 292 |
+
"anchor_bbox": [
|
| 293 |
+
159,
|
| 294 |
+
506,
|
| 295 |
+
599,
|
| 296 |
+
908
|
| 297 |
+
],
|
| 298 |
+
"target_pixels": 118754,
|
| 299 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02131/view_03_left/rgb.png",
|
| 300 |
+
"ok": true
|
| 301 |
+
}
|
| 302 |
+
],
|
| 303 |
+
"all_views_ok": true
|
| 304 |
+
}
|
data/batch_v5/pair_02139/meta.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2139,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "65a778d8-41c9-4b61-b12c-c55d152a66fd",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "5894e989-ba18-4007-a1ca-6dc2c517c212#471",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-0.21615782380104065,
|
| 13 |
+
-7.1241455078125,
|
| 14 |
+
0.4698309898376465
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-2.0361440181732178,
|
| 19 |
+
-6.956974029541016,
|
| 20 |
+
1.3976400792598724
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.45061593295091373,
|
| 41 |
+
0.42020688532987127,
|
| 42 |
+
-0.7876366259209547,
|
| 43 |
+
-3.333275438701779
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.8927179179174,
|
| 47 |
+
0.21210722207419347,
|
| 48 |
+
-0.3975742010910556,
|
| 49 |
+
-8.154646820955287
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.8822905983095009,
|
| 54 |
+
0.47070510952682765,
|
| 55 |
+
2.2527508693619005
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-3.333275438701779,
|
| 66 |
+
-8.154646820955287,
|
| 67 |
+
2.2527508693619005
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 9,
|
| 71 |
+
"dist": 2.0496647914396378,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.48467587547624635,
|
| 76 |
+
0.04464239220451671,
|
| 77 |
+
-1.900337036768743
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.484675875476249,
|
| 81 |
+
-0.04464239220451516,
|
| 82 |
+
-3.704086234264243
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
0,
|
| 87 |
+
262,
|
| 88 |
+
493,
|
| 89 |
+
803
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
359,
|
| 93 |
+
353,
|
| 94 |
+
917,
|
| 95 |
+
685
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 109267,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02139/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 270,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.8927179179174001,
|
| 108 |
+
0.21210722207419347,
|
| 109 |
+
-0.3975742010910556,
|
| 110 |
+
-2.2402379732656588
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.45061593295091373,
|
| 114 |
+
-0.4202068853298713,
|
| 115 |
+
0.7876366259209548,
|
| 116 |
+
-4.833435250962108
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.8822905983095011,
|
| 121 |
+
0.47070510952682765,
|
| 122 |
+
2.2527508693619005
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-2.2402379732656588,
|
| 133 |
+
-4.833435250962108,
|
| 134 |
+
2.2527508693619005
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 3,
|
| 138 |
+
"dist": 2.0496647914396378,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.7747020772171274,
|
| 143 |
+
0.18115920726060608,
|
| 144 |
+
-2.1562244278281346
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.7747020772171265,
|
| 148 |
+
-0.18115920726060697,
|
| 149 |
+
-3.4481988432048487
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
0,
|
| 154 |
+
0,
|
| 155 |
+
0,
|
| 156 |
+
0
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
0,
|
| 160 |
+
359,
|
| 161 |
+
366,
|
| 162 |
+
756
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 0,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02139/view_01_right/rgb.png",
|
| 166 |
+
"ok": false
|
| 167 |
+
}
|
| 168 |
+
],
|
| 169 |
+
"all_views_ok": false
|
| 170 |
+
}
|
data/batch_v5/pair_02141/meta.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2141,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "76f93ffd-7dcc-411e-9075-29c738a97646",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "1f870eb0-9894-42b3-9576-e33a111bc265#408",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.0929793119430542,
|
| 13 |
+
-1.3421283960342407,
|
| 14 |
+
0.42999351024627686
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-1.1045764535665512,
|
| 19 |
+
-0.7033045440912247,
|
| 20 |
+
1.3749870955944061
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.992340261053309,
|
| 41 |
+
-0.10102434829391022,
|
| 42 |
+
0.07109773093736062,
|
| 43 |
+
-0.9674060837453722
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.1235346360040398,
|
| 47 |
+
-0.8115175743541342,
|
| 48 |
+
0.5711203202668695,
|
| 49 |
+
0.03257886686445888
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5755287200185347,
|
| 54 |
+
0.8177815676779632,
|
| 55 |
+
2.413557313445033
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-0.9674060837453722,
|
| 66 |
+
0.03257886686445888,
|
| 67 |
+
2.413557313445033
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 2,
|
| 71 |
+
"dist": 1.140720510841398,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.045212591283306014,
|
| 76 |
+
0.013312879753680118,
|
| 77 |
+
-1.27935405228774
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.045212591283306236,
|
| 81 |
+
-0.013312879753679674,
|
| 82 |
+
-2.4161731404203732
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
353,
|
| 87 |
+
20,
|
| 88 |
+
696,
|
| 89 |
+
894
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
324,
|
| 93 |
+
172,
|
| 94 |
+
779,
|
| 95 |
+
980
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 116901,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02141/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.12353463600403958,
|
| 108 |
+
0.8115175743541342,
|
| 109 |
+
-0.5711203202668695,
|
| 110 |
+
-2.1540732196819943
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.992340261053309,
|
| 114 |
+
-0.10102434829391004,
|
| 115 |
+
0.07109773093736049,
|
| 116 |
+
-0.8913446710533024
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.5755287200185347,
|
| 121 |
+
0.8177815676779632,
|
| 122 |
+
2.413557313445033
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-2.1540732196819943,
|
| 133 |
+
-0.8913446710533024,
|
| 134 |
+
2.413557313445033
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.140720510841398,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.31624898966753356,
|
| 143 |
+
0.2349614505221223,
|
| 144 |
+
-1.435343283728248
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.31624898966753356,
|
| 148 |
+
-0.2349614505221223,
|
| 149 |
+
-2.260183908979865
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
0,
|
| 154 |
+
0,
|
| 155 |
+
0,
|
| 156 |
+
0
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
253,
|
| 160 |
+
703,
|
| 161 |
+
1023,
|
| 162 |
+
875
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 0,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02141/view_01_right/rgb.png",
|
| 166 |
+
"ok": false
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.992340261053309,
|
| 175 |
+
0.10794701942877333,
|
| 176 |
+
-0.06006868809200497,
|
| 177 |
+
-1.230149681764233
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.12353463600403956,
|
| 181 |
+
0.867126636746416,
|
| 182 |
+
-0.48252522167467926,
|
| 183 |
+
-2.0780118069899243
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.486249767960143,
|
| 188 |
+
0.8738198688280708,
|
| 189 |
+
2.813557313445033
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-1.230149681764233,
|
| 200 |
+
-2.0780118069899243,
|
| 201 |
+
2.813557313445033
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 12,
|
| 205 |
+
"dist": 1.140720510841398,
|
| 206 |
+
"lr": "left",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
-0.045212591283306236,
|
| 210 |
+
0.5060961064679702,
|
| 211 |
+
-1.9279251849075036
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
0.045212591283306125,
|
| 215 |
+
-0.5060961064679697,
|
| 216 |
+
-2.446127360012839
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
417,
|
| 221 |
+
0,
|
| 222 |
+
641,
|
| 223 |
+
534
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
331,
|
| 227 |
+
358,
|
| 228 |
+
763,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 72686,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02141/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"view_idx": 3,
|
| 237 |
+
"view_label": "left",
|
| 238 |
+
"azimuth_offset_deg": 270,
|
| 239 |
+
"cam2world": [
|
| 240 |
+
[
|
| 241 |
+
0.12353463600403979,
|
| 242 |
+
-0.867126636746416,
|
| 243 |
+
0.48252522167467926,
|
| 244 |
+
-0.04348254582761113
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
0.992340261053309,
|
| 248 |
+
0.10794701942877352,
|
| 249 |
+
-0.06006868809200507,
|
| 250 |
+
-1.1540882690721632
|
| 251 |
+
],
|
| 252 |
+
[
|
| 253 |
+
-0.0,
|
| 254 |
+
0.486249767960143,
|
| 255 |
+
0.8738198688280708,
|
| 256 |
+
2.813557313445033
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
0.0,
|
| 260 |
+
0.0,
|
| 261 |
+
0.0,
|
| 262 |
+
1.0
|
| 263 |
+
]
|
| 264 |
+
],
|
| 265 |
+
"cam_pos_world": [
|
| 266 |
+
-0.04348254582761113,
|
| 267 |
+
-1.1540882690721632,
|
| 268 |
+
2.813557313445033
|
| 269 |
+
],
|
| 270 |
+
"gt": {
|
| 271 |
+
"clock": 2,
|
| 272 |
+
"dist": 1.140720510841398,
|
| 273 |
+
"lr": "right",
|
| 274 |
+
"fb": "in front of",
|
| 275 |
+
"target_cam_xyz": [
|
| 276 |
+
0.31624898966753334,
|
| 277 |
+
0.26925911638423194,
|
| 278 |
+
-1.79613379908442
|
| 279 |
+
],
|
| 280 |
+
"anchor_cam_xyz": [
|
| 281 |
+
-0.31624898966753356,
|
| 282 |
+
-0.2692591163842315,
|
| 283 |
+
-2.577918745835922
|
| 284 |
+
]
|
| 285 |
+
},
|
| 286 |
+
"target_bbox": [
|
| 287 |
+
476,
|
| 288 |
+
140,
|
| 289 |
+
986,
|
| 290 |
+
587
|
| 291 |
+
],
|
| 292 |
+
"anchor_bbox": [
|
| 293 |
+
0,
|
| 294 |
+
399,
|
| 295 |
+
797,
|
| 296 |
+
815
|
| 297 |
+
],
|
| 298 |
+
"target_pixels": 117958,
|
| 299 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02141/view_03_left/rgb.png",
|
| 300 |
+
"ok": true
|
| 301 |
+
}
|
| 302 |
+
],
|
| 303 |
+
"all_views_ok": false
|
| 304 |
+
}
|
data/batch_v5/pair_02144/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2144,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "5a7ad2f9-1461-4954-8cb1-2c99aeaa4fb4",
|
| 6 |
+
"target_category": "others",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "06beed0e-c97a-4110-943c-d5ef6eb988e8#398",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
-1.8382377624511719,
|
| 13 |
+
3.4047553539276123,
|
| 14 |
+
0.39500001072883606
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-0.9345728904008865,
|
| 19 |
+
1.7356888055801392,
|
| 20 |
+
1.3050000667572021
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.3401840135858986,
|
| 41 |
+
0.741205806333939,
|
| 42 |
+
-0.5786957659750455,
|
| 43 |
+
-3.5792413487758847
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9403588872875022,
|
| 47 |
+
0.2681384410787849,
|
| 48 |
+
-0.2093488464626683,
|
| 49 |
+
1.7769422274514415
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.615398837399531,
|
| 54 |
+
0.7882158783780656,
|
| 55 |
+
3.8367648867341275
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-3.5792413487758847,
|
| 66 |
+
1.7769422274514415,
|
| 67 |
+
3.8367648867341275
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 2,
|
| 71 |
+
"dist": 2.1048737362991243,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.9384669526617375,
|
| 76 |
+
0.391136862163206,
|
| 77 |
+
-3.5173993144127653
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.938466952661738,
|
| 81 |
+
-0.3911368621632063,
|
| 82 |
+
-4.061145929149342
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
698,
|
| 87 |
+
309,
|
| 88 |
+
798,
|
| 89 |
+
512
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
53,
|
| 93 |
+
430,
|
| 94 |
+
521,
|
| 95 |
+
773
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 6931,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02144/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.4243877230921837,
|
| 108 |
+
-0.7137141618971694,
|
| 109 |
+
0.5572316893322322,
|
| 110 |
+
0.7250974579494036
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.9054805688078746,
|
| 114 |
+
0.33450914192997283,
|
| 115 |
+
-0.261167711397564,
|
| 116 |
+
1.580586421261871
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.6153988373995313,
|
| 121 |
+
0.7882158783780656,
|
| 122 |
+
3.8367648867341275
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
0.7250974579494036,
|
| 133 |
+
1.580586421261871,
|
| 134 |
+
3.8367648867341275
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 8,
|
| 138 |
+
"dist": 2.1048737362991243,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.5639015250440278,
|
| 143 |
+
-0.3216317295948259,
|
| 144 |
+
-2.9609058781153506
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.5639015250440274,
|
| 148 |
+
0.32163172959482633,
|
| 149 |
+
-4.617639365446754
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
292,
|
| 154 |
+
523,
|
| 155 |
+
393,
|
| 156 |
+
703
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
426,
|
| 160 |
+
298,
|
| 161 |
+
828,
|
| 162 |
+
611
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 7528,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02144/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.9054805688078744,
|
| 175 |
+
-0.33450914192997283,
|
| 176 |
+
0.26116771139756406,
|
| 177 |
+
-0.39676966793402424
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.4243877230921837,
|
| 181 |
+
-0.7137141618971692,
|
| 182 |
+
0.5572316893322322,
|
| 183 |
+
4.6817248641293085
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.6153988373995312,
|
| 188 |
+
0.7882158783780656,
|
| 189 |
+
3.8367648867341275
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-0.39676966793402424,
|
| 200 |
+
4.6817248641293085,
|
| 201 |
+
3.8367648867341275
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 10,
|
| 205 |
+
"dist": 2.1048737362991243,
|
| 206 |
+
"lr": "left",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
-0.7632911672491507,
|
| 210 |
+
0.7244826241379912,
|
| 211 |
+
-3.7776587179577263
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
0.7632911672491516,
|
| 215 |
+
-0.7244826241379921,
|
| 216 |
+
-3.800886525604379
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
300,
|
| 221 |
+
239,
|
| 222 |
+
372,
|
| 223 |
+
440
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
516,
|
| 227 |
+
449,
|
| 228 |
+
813,
|
| 229 |
+
951
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 6186,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02144/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_02149/meta.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2149,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "6b76631e-d399-44dc-9f75-f24ed24ba555",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "737532dc-06aa-4b1e-8446-8027a05434b4#254",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
1.34904944896698,
|
| 13 |
+
-4.516462802886963,
|
| 14 |
+
0.20917999744415283
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
1.2177926301956177,
|
| 19 |
+
-3.718207597732544,
|
| 20 |
+
0.8696082383394241
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
0.41632964149594864,
|
| 41 |
+
0.6765821228009199,
|
| 42 |
+
-0.6073765394860556,
|
| 43 |
+
-0.0559055883188424
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.9092137425335447,
|
| 47 |
+
0.30980745170367074,
|
| 48 |
+
-0.2781181641982826,
|
| 49 |
+
-4.7306138483929585
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.6680239321873723,
|
| 54 |
+
0.7441397893036773,
|
| 55 |
+
2.1802975277234373
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-0.0559055883188424,
|
| 66 |
+
-4.7306138483929585,
|
| 67 |
+
2.1802975277234373
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 10,
|
| 71 |
+
"dist": 1.0443204423940595,
|
| 72 |
+
"lr": "left",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
-0.39021535343915525,
|
| 76 |
+
0.29984063212605244,
|
| 77 |
+
-2.0305190358122136
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
0.3902153534391557,
|
| 81 |
+
-0.299840632126053,
|
| 82 |
+
-2.379683007992247
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
28,
|
| 87 |
+
124,
|
| 88 |
+
576,
|
| 89 |
+
615
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
542,
|
| 93 |
+
494,
|
| 94 |
+
794,
|
| 95 |
+
762
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 180234,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02149/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9092137425335447,
|
| 108 |
+
-0.3098074517036706,
|
| 109 |
+
0.27811816419828256,
|
| 110 |
+
1.896699687664504
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.41632964149594853,
|
| 114 |
+
0.6765821228009198,
|
| 115 |
+
-0.6073765394860556,
|
| 116 |
+
-5.456661828209895
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.6680239321873722,
|
| 121 |
+
0.7441397893036772,
|
| 122 |
+
2.1802975277234373
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
1.896699687664504,
|
| 133 |
+
-5.456661828209895,
|
| 134 |
+
2.1802975277234373
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 12,
|
| 138 |
+
"dist": 1.0443204423940595,
|
| 139 |
+
"lr": "right",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
0.10649839997802824,
|
| 143 |
+
0.5109657060964987,
|
| 144 |
+
-2.2200487506915367
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
-0.10649839997802824,
|
| 148 |
+
-0.5109657060964969,
|
| 149 |
+
-2.190153293112921
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
413,
|
| 154 |
+
42,
|
| 155 |
+
756,
|
| 156 |
+
578
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
347,
|
| 160 |
+
575,
|
| 161 |
+
595,
|
| 162 |
+
872
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 115665,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02149/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.4163296414959486,
|
| 175 |
+
-0.7372393528074387,
|
| 176 |
+
0.5321163089813391,
|
| 177 |
+
2.6227476674814403
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.9092137425335447,
|
| 181 |
+
-0.33758244194126,
|
| 182 |
+
0.24365644929104768,
|
| 183 |
+
-3.5040565522265483
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.585248862933577,
|
| 188 |
+
0.8108537281377913,
|
| 189 |
+
2.5802975277234372
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
2.6227476674814403,
|
| 200 |
+
-3.5040565522265483,
|
| 201 |
+
2.5802975277234372
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 2,
|
| 205 |
+
"dist": 1.0443204423940595,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.3902153534391548,
|
| 210 |
+
0.10690281385369604,
|
| 211 |
+
-2.186897560067644
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.3902153534391566,
|
| 215 |
+
-0.10690281385369615,
|
| 216 |
+
-2.84706439634783
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
448,
|
| 221 |
+
232,
|
| 222 |
+
942,
|
| 223 |
+
674
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
291,
|
| 227 |
+
436,
|
| 228 |
+
484,
|
| 229 |
+
658
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 130054,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02149/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"view_idx": 3,
|
| 237 |
+
"view_label": "left",
|
| 238 |
+
"azimuth_offset_deg": 270,
|
| 239 |
+
"cam2world": [
|
| 240 |
+
[
|
| 241 |
+
-0.9092137425335448,
|
| 242 |
+
0.30980745170367063,
|
| 243 |
+
-0.2781181641982825,
|
| 244 |
+
0.670142391498094
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
-0.4163296414959485,
|
| 248 |
+
-0.6765821228009199,
|
| 249 |
+
0.6073765394860557,
|
| 250 |
+
-2.778008572409612
|
| 251 |
+
],
|
| 252 |
+
[
|
| 253 |
+
0.0,
|
| 254 |
+
0.6680239321873724,
|
| 255 |
+
0.7441397893036773,
|
| 256 |
+
2.1802975277234373
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
0.0,
|
| 260 |
+
0.0,
|
| 261 |
+
0.0,
|
| 262 |
+
1.0
|
| 263 |
+
]
|
| 264 |
+
],
|
| 265 |
+
"cam_pos_world": [
|
| 266 |
+
0.670142391498094,
|
| 267 |
+
-2.778008572409612,
|
| 268 |
+
2.1802975277234373
|
| 269 |
+
],
|
| 270 |
+
"gt": {
|
| 271 |
+
"clock": 8,
|
| 272 |
+
"dist": 1.0443204423940595,
|
| 273 |
+
"lr": "left",
|
| 274 |
+
"fb": "in front of",
|
| 275 |
+
"target_cam_xyz": [
|
| 276 |
+
-0.10649839997802835,
|
| 277 |
+
-0.06978383568604896,
|
| 278 |
+
-1.6987023610829164
|
| 279 |
+
],
|
| 280 |
+
"anchor_cam_xyz": [
|
| 281 |
+
0.10649839997802812,
|
| 282 |
+
0.06978383568604896,
|
| 283 |
+
-2.7114996827215423
|
| 284 |
+
]
|
| 285 |
+
},
|
| 286 |
+
"target_bbox": [
|
| 287 |
+
267,
|
| 288 |
+
199,
|
| 289 |
+
702,
|
| 290 |
+
907
|
| 291 |
+
],
|
| 292 |
+
"anchor_bbox": [
|
| 293 |
+
565,
|
| 294 |
+
376,
|
| 295 |
+
653,
|
| 296 |
+
493
|
| 297 |
+
],
|
| 298 |
+
"target_pixels": 168661,
|
| 299 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02149/view_03_left/rgb.png",
|
| 300 |
+
"ok": true
|
| 301 |
+
}
|
| 302 |
+
],
|
| 303 |
+
"all_views_ok": true
|
| 304 |
+
}
|
data/batch_v5/pair_02152/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2152,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "102c7436-d583-4de3-bfd6-1409f3ab9f52",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "3f4bdfd2-1c63-435d-9482-6dce589f6a5f#576",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
-9.227668762207031,
|
| 13 |
+
-0.6186809539794922,
|
| 14 |
+
0.4602329730987549
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
-8.026622891426086,
|
| 19 |
+
0.6062679477035999,
|
| 20 |
+
1.4137542843818665
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.5219004039975415,
|
| 41 |
+
-0.6725182351801645,
|
| 42 |
+
0.5247277309780376,
|
| 43 |
+
-6.462057567015862
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.8530064292296998,
|
| 47 |
+
-0.41147115263034745,
|
| 48 |
+
0.3210475389188497,
|
| 49 |
+
1.3184733571307723
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.6151509683835424,
|
| 54 |
+
0.7884093391740041,
|
| 55 |
+
4.190063179650527
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
-6.462057567015862,
|
| 66 |
+
1.3184733571307723,
|
| 67 |
+
4.190063179650527
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 5,
|
| 71 |
+
"dist": 1.962705756481505,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.20903148171669095,
|
| 76 |
+
-0.36259841393334735,
|
| 77 |
+
-3.2384904680076536
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.20903148171669184,
|
| 81 |
+
0.36259841393334735,
|
| 82 |
+
-5.0137444796868325
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
423,
|
| 87 |
+
508,
|
| 88 |
+
726,
|
| 89 |
+
722
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
99,
|
| 93 |
+
213,
|
| 94 |
+
881,
|
| 95 |
+
649
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 28059,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02152/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 135,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.23412731573338316,
|
| 108 |
+
0.7664962468550673,
|
| 109 |
+
-0.5980534287039716,
|
| 110 |
+
-11.094784529286272
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.9722059452747039,
|
| 114 |
+
-0.18458816227994004,
|
| 115 |
+
0.1440236449984301,
|
| 116 |
+
0.5880519751372484
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.6151509683835426,
|
| 121 |
+
0.7884093391740041,
|
| 122 |
+
4.190063179650527
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
-11.094784529286272,
|
| 133 |
+
0.5880519751372484,
|
| 134 |
+
4.190063179650527
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 10,
|
| 138 |
+
"dist": 1.962705756481505,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.7360501253363136,
|
| 143 |
+
0.6405228218080046,
|
| 144 |
+
-4.021168918035752
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.7360501253363139,
|
| 148 |
+
-0.6405228218080046,
|
| 149 |
+
-4.231066029658732
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
209,
|
| 154 |
+
238,
|
| 155 |
+
438,
|
| 156 |
+
454
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
751,
|
| 160 |
+
432,
|
| 161 |
+
980,
|
| 162 |
+
543
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 24287,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02152/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 225,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.9722059452747039,
|
| 175 |
+
0.18458816227994035,
|
| 176 |
+
-0.14402364499843032,
|
| 177 |
+
-9.221404305091754
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.23412731573338355,
|
| 181 |
+
0.7664962468550673,
|
| 182 |
+
-0.5980534287039715,
|
| 183 |
+
-2.473845205607659
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.6151509683835426,
|
| 188 |
+
0.7884093391740041,
|
| 189 |
+
4.190063179650527
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
-9.221404305091754,
|
| 200 |
+
-2.473845205607659,
|
| 201 |
+
4.190063179650527
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 1,
|
| 205 |
+
"dist": 1.962705756481505,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "behind",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.4404349689296261,
|
| 210 |
+
0.8735885719204217,
|
| 211 |
+
-4.20301686776818
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.4404349689296243,
|
| 215 |
+
-0.8735885719204219,
|
| 216 |
+
-4.049218079926305
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
517,
|
| 221 |
+
191,
|
| 222 |
+
728,
|
| 223 |
+
400
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
172,
|
| 227 |
+
381,
|
| 228 |
+
751,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 21025,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02152/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_02153/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2153,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "fceb092a-aed7-44e1-a711-7273689cf0b7",
|
| 6 |
+
"target_category": "cabinet",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "fb13fb08-cd1a-46d5-b044-9b13bf160622#819",
|
| 9 |
+
"category": "Table",
|
| 10 |
+
"raw_cat": "front3d_cat36",
|
| 11 |
+
"center": [
|
| 12 |
+
1.6831876039505005,
|
| 13 |
+
1.2928894758224487,
|
| 14 |
+
0.3408685028553009
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
2.117588311433792,
|
| 19 |
+
2.3335652351379395,
|
| 20 |
+
1.1967270374298096
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.18336618195129553,
|
| 41 |
+
-0.7899891821193437,
|
| 42 |
+
0.5850589162221314,
|
| 43 |
+
3.4679189809549786
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
0.9830446802239482,
|
| 47 |
+
-0.1473557642110943,
|
| 48 |
+
0.1091303598324499,
|
| 49 |
+
2.105617095853371
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.5951498726272022,
|
| 54 |
+
0.8036147267887921,
|
| 55 |
+
2.9218989024634676
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
3.4679189809549786,
|
| 66 |
+
2.105617095853371,
|
| 67 |
+
2.9218989024634676
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 1.4156990647354695,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.47168818493247944,
|
| 76 |
+
0.006421333206118929,
|
| 77 |
+
-2.1515204525710425
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.47168818493247877,
|
| 81 |
+
-0.006421333206118929,
|
| 82 |
+
-3.2070203022123014
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
515,
|
| 87 |
+
386,
|
| 88 |
+
1010,
|
| 89 |
+
673
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
261,
|
| 93 |
+
436,
|
| 94 |
+
478,
|
| 95 |
+
632
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 120921,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02153/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 90,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
-0.9830446802239482,
|
| 108 |
+
0.1473557642110943,
|
| 109 |
+
-0.1091303598324499,
|
| 110 |
+
1.6079982173189693
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
-0.18336618195129553,
|
| 114 |
+
-0.7899891821193437,
|
| 115 |
+
0.5850589162221314,
|
| 116 |
+
3.3807583787430264
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
0.0,
|
| 120 |
+
0.5951498726272022,
|
| 121 |
+
0.8036147267887921,
|
| 122 |
+
2.9218989024634676
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
1.6079982173189693,
|
| 133 |
+
3.3807583787430264,
|
| 134 |
+
2.9218989024634676
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 8,
|
| 138 |
+
"dist": 1.4156990647354695,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "in front of",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.30893002260595814,
|
| 143 |
+
-0.1243735229445545,
|
| 144 |
+
-2.0546549529933764
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.3089300226059577,
|
| 148 |
+
0.12437352294455395,
|
| 149 |
+
-3.303885801789969
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
195,
|
| 154 |
+
264,
|
| 155 |
+
466,
|
| 156 |
+
835
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
511,
|
| 160 |
+
373,
|
| 161 |
+
691,
|
| 162 |
+
582
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 103332,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02153/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 180,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
0.18336618195129525,
|
| 175 |
+
0.7899891821193437,
|
| 176 |
+
-0.5850589162221314,
|
| 177 |
+
0.33285693442931374
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
-0.9830446802239482,
|
| 181 |
+
0.1473557642110941,
|
| 182 |
+
-0.10913035983244973,
|
| 183 |
+
1.5208376151070175
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.5951498726272021,
|
| 188 |
+
0.8036147267887921,
|
| 189 |
+
2.9218989024634676
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
0.33285693442931374,
|
| 200 |
+
1.5208376151070175,
|
| 201 |
+
2.9218989024634676
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 11,
|
| 205 |
+
"dist": 1.4156990647354695,
|
| 206 |
+
"lr": "left",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
-0.471688184932479,
|
| 210 |
+
0.5029427646328037,
|
| 211 |
+
-2.5192397797803516
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
0.4716881849324792,
|
| 215 |
+
-0.5029427646328037,
|
| 216 |
+
-2.8393009750029923
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
134,
|
| 221 |
+
133,
|
| 222 |
+
508,
|
| 223 |
+
490
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
551,
|
| 227 |
+
554,
|
| 228 |
+
775,
|
| 229 |
+
792
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 107627,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02153/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|
data/batch_v5/pair_02177/meta.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pair_idx": 2177,
|
| 3 |
+
"scene": "front3d:random",
|
| 4 |
+
"target_source": "3dfuture",
|
| 5 |
+
"target_id": "d8732fb3-49f9-4258-8530-e21c97cae7ef",
|
| 6 |
+
"target_category": "others",
|
| 7 |
+
"anchor": {
|
| 8 |
+
"jid": "c914d995-3ce6-4992-9b2c-1d846958b74d#342",
|
| 9 |
+
"category": "Sofa",
|
| 10 |
+
"raw_cat": "front3d_cat46",
|
| 11 |
+
"center": [
|
| 12 |
+
3.993185043334961,
|
| 13 |
+
-0.841065526008606,
|
| 14 |
+
0.41411659121513367
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"pos_A": [
|
| 18 |
+
3.386929512023926,
|
| 19 |
+
0.03064262866973877,
|
| 20 |
+
1.3432331085205078
|
| 21 |
+
],
|
| 22 |
+
"target_color_rgb": [
|
| 23 |
+
0.5,
|
| 24 |
+
0.5,
|
| 25 |
+
0.5
|
| 26 |
+
],
|
| 27 |
+
"anchor_color_rgb": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"n_views": 4,
|
| 33 |
+
"views": [
|
| 34 |
+
{
|
| 35 |
+
"view_idx": 0,
|
| 36 |
+
"view_label": "front",
|
| 37 |
+
"azimuth_offset_deg": 0,
|
| 38 |
+
"cam2world": [
|
| 39 |
+
[
|
| 40 |
+
-0.9930697290441526,
|
| 41 |
+
0.08039839939610115,
|
| 42 |
+
-0.08572403764825018,
|
| 43 |
+
3.482492525663722
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
-0.11752664913190375,
|
| 47 |
+
-0.6793456402748409,
|
| 48 |
+
0.7243459034076144,
|
| 49 |
+
1.348656917066301
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
0.0,
|
| 53 |
+
0.7294008489260976,
|
| 54 |
+
0.6840865453916547,
|
| 55 |
+
2.5350626968115733
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
0.0,
|
| 59 |
+
0.0,
|
| 60 |
+
0.0,
|
| 61 |
+
1.0
|
| 62 |
+
]
|
| 63 |
+
],
|
| 64 |
+
"cam_pos_world": [
|
| 65 |
+
3.482492525663722,
|
| 66 |
+
1.348656917066301,
|
| 67 |
+
2.5350626968115733
|
| 68 |
+
],
|
| 69 |
+
"gt": {
|
| 70 |
+
"clock": 3,
|
| 71 |
+
"dist": 1.4109140225072605,
|
| 72 |
+
"lr": "right",
|
| 73 |
+
"fb": "in front of",
|
| 74 |
+
"target_cam_xyz": [
|
| 75 |
+
0.24980253888513326,
|
| 76 |
+
0.01838263382929961,
|
| 77 |
+
-1.7618207888033066
|
| 78 |
+
],
|
| 79 |
+
"anchor_cam_xyz": [
|
| 80 |
+
-0.2498025388851337,
|
| 81 |
+
-0.01838263382929939,
|
| 82 |
+
-3.0808058001919028
|
| 83 |
+
]
|
| 84 |
+
},
|
| 85 |
+
"target_bbox": [
|
| 86 |
+
527,
|
| 87 |
+
174,
|
| 88 |
+
840,
|
| 89 |
+
804
|
| 90 |
+
],
|
| 91 |
+
"anchor_bbox": [
|
| 92 |
+
20,
|
| 93 |
+
338,
|
| 94 |
+
825,
|
| 95 |
+
716
|
| 96 |
+
],
|
| 97 |
+
"target_pixels": 147679,
|
| 98 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02177/view_00_front/rgb.png",
|
| 99 |
+
"ok": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"view_idx": 1,
|
| 103 |
+
"view_label": "right",
|
| 104 |
+
"azimuth_offset_deg": 180,
|
| 105 |
+
"cam2world": [
|
| 106 |
+
[
|
| 107 |
+
0.9930697290441525,
|
| 108 |
+
-0.08039839939610062,
|
| 109 |
+
0.08572403764824964,
|
| 110 |
+
3.8976220296951634
|
| 111 |
+
],
|
| 112 |
+
[
|
| 113 |
+
0.11752664913190297,
|
| 114 |
+
0.6793456402748408,
|
| 115 |
+
-0.7243459034076145,
|
| 116 |
+
-2.1590798144051684
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
-0.0,
|
| 120 |
+
0.7294008489260975,
|
| 121 |
+
0.6840865453916547,
|
| 122 |
+
2.5350626968115733
|
| 123 |
+
],
|
| 124 |
+
[
|
| 125 |
+
0.0,
|
| 126 |
+
0.0,
|
| 127 |
+
0.0,
|
| 128 |
+
1.0
|
| 129 |
+
]
|
| 130 |
+
],
|
| 131 |
+
"cam_pos_world": [
|
| 132 |
+
3.8976220296951634,
|
| 133 |
+
-2.1590798144051684,
|
| 134 |
+
2.5350626968115733
|
| 135 |
+
],
|
| 136 |
+
"gt": {
|
| 137 |
+
"clock": 11,
|
| 138 |
+
"dist": 1.4109140225072605,
|
| 139 |
+
"lr": "left",
|
| 140 |
+
"fb": "behind",
|
| 141 |
+
"target_cam_xyz": [
|
| 142 |
+
-0.2498025388851337,
|
| 143 |
+
0.6593157426444993,
|
| 144 |
+
-2.4452096916021433
|
| 145 |
+
],
|
| 146 |
+
"anchor_cam_xyz": [
|
| 147 |
+
0.24980253888513415,
|
| 148 |
+
-0.6593157426444999,
|
| 149 |
+
-2.3974168973930654
|
| 150 |
+
]
|
| 151 |
+
},
|
| 152 |
+
"target_bbox": [
|
| 153 |
+
326,
|
| 154 |
+
33,
|
| 155 |
+
497,
|
| 156 |
+
497
|
| 157 |
+
],
|
| 158 |
+
"anchor_bbox": [
|
| 159 |
+
64,
|
| 160 |
+
525,
|
| 161 |
+
1023,
|
| 162 |
+
1023
|
| 163 |
+
],
|
| 164 |
+
"target_pixels": 64004,
|
| 165 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02177/view_01_right/rgb.png",
|
| 166 |
+
"ok": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"view_idx": 2,
|
| 170 |
+
"view_label": "back",
|
| 171 |
+
"azimuth_offset_deg": 270,
|
| 172 |
+
"cam2world": [
|
| 173 |
+
[
|
| 174 |
+
-0.11752664913190301,
|
| 175 |
+
-0.6793456402748408,
|
| 176 |
+
0.7243459034076145,
|
| 177 |
+
5.443925643415178
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
0.9930697290441525,
|
| 181 |
+
-0.08039839939610065,
|
| 182 |
+
0.08572403764824967,
|
| 183 |
+
-0.1976466966537135
|
| 184 |
+
],
|
| 185 |
+
[
|
| 186 |
+
0.0,
|
| 187 |
+
0.7294008489260975,
|
| 188 |
+
0.6840865453916547,
|
| 189 |
+
2.5350626968115733
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
0.0,
|
| 193 |
+
0.0,
|
| 194 |
+
0.0,
|
| 195 |
+
1.0
|
| 196 |
+
]
|
| 197 |
+
],
|
| 198 |
+
"cam_pos_world": [
|
| 199 |
+
5.443925643415178,
|
| 200 |
+
-0.1976466966537135,
|
| 201 |
+
2.5350626968115733
|
| 202 |
+
],
|
| 203 |
+
"gt": {
|
| 204 |
+
"clock": 1,
|
| 205 |
+
"dist": 1.4109140225072605,
|
| 206 |
+
"lr": "right",
|
| 207 |
+
"fb": "in front of",
|
| 208 |
+
"target_cam_xyz": [
|
| 209 |
+
0.46845908104233475,
|
| 210 |
+
0.5097357440928949,
|
| 211 |
+
-2.285721424129436
|
| 212 |
+
],
|
| 213 |
+
"anchor_cam_xyz": [
|
| 214 |
+
-0.4684590810423348,
|
| 215 |
+
-0.5097357440928958,
|
| 216 |
+
-2.556905164865773
|
| 217 |
+
]
|
| 218 |
+
},
|
| 219 |
+
"target_bbox": [
|
| 220 |
+
539,
|
| 221 |
+
86,
|
| 222 |
+
928,
|
| 223 |
+
509
|
| 224 |
+
],
|
| 225 |
+
"anchor_bbox": [
|
| 226 |
+
0,
|
| 227 |
+
360,
|
| 228 |
+
548,
|
| 229 |
+
1023
|
| 230 |
+
],
|
| 231 |
+
"target_pixels": 132472,
|
| 232 |
+
"rgb": "/data222/hongbo.wang/Spatial_MLLM/mgeo_dpo/render_out/batch_v5/pair_02177/view_02_back/rgb.png",
|
| 233 |
+
"ok": true
|
| 234 |
+
}
|
| 235 |
+
],
|
| 236 |
+
"all_views_ok": true
|
| 237 |
+
}
|