publish pear_parameter_network bundle (schema v3, ascend_310p)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+artifacts/ascend_310p/pear_parameter_network_bs1.om filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,201 @@
+---
+license: apache-2.0
+pipeline_tag: image-to-3d
+tags:
+- pear
+- human-mesh-recovery
+- smplx
+- robotics
+- IB-Robot
+- ascend
+- edge-deployment
+base_model:
+- BestWJH/PEAR_models
+---
+
+# Model Card for PEAR Parameter Network (IB-Robot)
+
+The parameter-regression network of PEAR (Pixel-aligned Expressive humAn mesh Recovery),
+packaged for the [IB-Robot](https://atomgit.com/openeuler/IB_Robot) framework. From a
+person crop it regresses SMPL-X / FLAME / camera parameters for expressive 3D human
+understanding in HRI.
+
+Person crops come from
+[openEuler/yolox_x_640](https://huggingface.co/openEuler/yolox_x_640).
+
+**Scope:** this bundle contains the PEAR image encoder and parameter regression heads only.
+EHM / SMPL-X LBS, mesh generation and rendering stay on the host CPU and are **not** part of
+the OM.
+
+## Repository Structure
+
+- `inference_manifest.json` — deployment routing (schema v3)
+- `assets/adapter.json` — adapter identity (`pear_parameter_network` / `predict_parameters`)
+- `assets/pear_model.pt` — original PyTorch checkpoint the OM was converted from
+- `artifacts/ascend_310p/pear_parameter_network_bs1.om` — Ascend 310P1 OM (batch 1)
+
+## Deployment Backends
+
+| Target | Backend | Runtime | Hardware |
+|--------|---------|---------|----------|
+| `ascend_310p` | ascend | ACL | Ascend 310P1 |
+
+**Input:** `pear.input` float32 [1,3,256,256] NCHW (`input`)
+
+**Outputs:** eight tensors, fixed order
+
+| # | semantic | shape |
+|---|----------|-------|
+| 0 | `smplx_pose_raw` | [1,312] |
+| 1 | `smplx_scale` | [1,6] |
+| 2 | `smplx_shape` | [1,200] |
+| 3 | `smplx_expression` | [1,50] |
+| 4 | `flame_pose` | [1,14] |
+| 5 | `flame_shape` | [1,300] |
+| 6 | `flame_expression` | [1,50] |
+| 7 | `camera_raw` | [1,3] |
+
+`smplx_pose_raw` splits as:
+
+```text
+0:6       global_orient
+6:132     body_pose,       21 × 6D
+132:222   left_hand_pose,  15 × 6D
+222:312   right_hand_pose, 15 × 6D
+```
+
+The 6D values are **not** Euler angles: decode to rotation matrices first, then to
+axis-angle radians if needed.
+
+### Preprocessing contract (`pear-rgb-crop256-bgr-imagenet-v1`)
+
+```text
+person bbox xyxy in source-image coordinates
+→ centre (cx, cy), side = max(w, h) × 1.25
+→ square affine crop (cv2.INTER_LINEAR, BORDER_CONSTANT 0)
+→ 256×256 BGR
+→ NCHW float32, divided by 255
+→ ImageNet normalize (mean 0.485/0.456/0.406, std 0.229/0.224/0.225)
+→ width slice [:, :, :, 32:-32]
+```
+
+The backbone therefore sees 256×192 content. Crops must be taken in source-video
+coordinates, not in YOLOX's 640×640 letterbox space.
+
+## Source Model
+
+This bundle's torch weights (`assets/pear_model.pt`) are the upstream PEAR checkpoint,
+unmodified:
+
+- **Model weights (HuggingFace):** [BestWJH/PEAR_models](https://huggingface.co/BestWJH/PEAR_models) — `pear_model.pt`, fetched by upstream code via `hf_hub_download(repo_id="BestWJH/PEAR_models", filename="pear_model.pt")`
+- **Project page:** <https://wujh2001.github.io/PEAR/>
+- `pear_model.pt` — 2,685,908,343 bytes, sha256 `be82dfa06e7b0608c6440058dfa0794d9b2ceee69f6e5b09bf41bb0076abeb18`
+
+Upstream states this is the *initial* release of the PEAR model rather than the final version
+presented in the paper; it may underperform on complex poses.
+
+### Source code
+
+```bash
+git clone https://github.com/Pixel-Talk/PEAR.git
+git -C PEAR checkout 230fa1534367c9f357c1c192a328cdc87ab4491c
+```
+
+- **Repository:** <https://github.com/Pixel-Talk/PEAR> (Apache-2.0)
+- **Commit:** `230fa1534367c9f357c1c192a328cdc87ab4491c` on `main` — 2026-08-01, *"Update app.py"*
+- The clone used for export carries no submodules (upstream has no `.gitmodules`) and no
+  local patches; the working tree differs from that commit only in file permission bits.
+
+The Ascend OM was converted from those weights via ONNX with external data
+(`pear_parameter_network_bs1.onnx` + `.data`, consolidated `.data` sha256
+`76d0b08fea2a17133aa62b718e1faaf329e0167a42638ffe63c177951b5ab766`), with ATC
+`--soc_version=Ascend310P1`. The OM (`pear_parameter_network_bs1.om`, sha256
+`67798d9f1da61fba4e5b706b20acf82cf2daf030a3239f89709e655421c84e81`) is not re-trained.
+
+## Assets Not Included
+
+Consuming the parameter outputs (rotation decode, parameter bookkeeping) needs `numpy` only.
+
+Reconstructing meshes / 3D joints additionally requires the SMPL-X, FLAME and MANO body
+models, which are **not** redistributed here because their licenses do not permit it.
+Obtain them yourself from the original sites and accept their terms:
+
+- SMPL-X — <https://smpl-x.is.tue.mpg.de/> (`SMPLX_NEUTRAL_2020.npz`)
+- FLAME 2020 — <https://flame.is.tue.mpg.de/> (`generic_model.pkl`)
+- MANO — <https://mano.is.tue.mpg.de/> (`MANO_LEFT.pkl`, `MANO_RIGHT.pkl`)
+
+These are research-licensed assets and are generally not usable for commercial deployment
+without a separate agreement.
+
+## Validation
+
+Board evidence recorded on a real Ascend 310P1 over a 368-frame, 30 FPS clip
+(`npu-smi info` SoC = `Ascend310P1`; `Ascend310P3` is not a valid target for this device).
+
+Numerical alignment vs. the PyTorch reference (strict gate passed):
+
+```text
+raw parameter max abs diff:   0.036261   (gate 0.05)
+rotation worst P95:           0.068421°  (gate 1.0°)
+body joint max:               0.332952°  (gate 5.0°)
+left  hand joint max:         0.211992°  (gate 5.0°)
+right hand joint max:         0.211410°  (gate 5.0°)
+left/right swap:              none (direct mean 0.027°, swapped mean 45.964°)
+NaN/Inf:                      none; rotation matrices orthonormal to ~1e-7
+```
+
+Latency, same run:
+
+```text
+OM only:                mean 26.298 ms, P95 27.559 ms, max 31.641 ms
+full ACL:               mean 27.784 ms, P95 29.602 ms, max 33.094 ms
+ACL + CPU parameter processing: mean 28.542 ms, P95 30.542 ms, max 33.929 ms
+```
+
+**Status: engineering `GO`, strict real-time `CONDITIONAL`.** Against a 33.33 ms budget at
+30 Hz, mean/P50/P95 fit, but the worst frame exceeds it by ~0.60 ms. Systems with a hard
+per-frame deadline must budget for that overrun.
+
+### Semantics caveats
+
+- Pose outputs are SMPL-X **local joint rotations**, not robot motor angles. Driving a robot
+  additionally requires a SMPL-X→joint mapping, axis transforms, zero offsets, sign and unit
+  conversion, joint limits and velocity/acceleration limits — none of which are in this bundle.
+- `camera_raw` and the recovered body are in relative/model coordinates. Without real camera
+  intrinsics and root depth they must not be presented as absolute camera XYZ.
+
+## Usage
+
+Select the `ascend_310p` deployment through the IB-Robot unified inference runtime; the
+bundle is consumed as an external model bundle (it is not stored in the IB-Robot Git
+repository).
+
+```python
+from inference_manifest import load_inference_manifest
+
+validated = load_inference_manifest("models/pear_parameter_network", "ascend_310p")
+```
+
+## License
+
+Code and packaging: Apache-2.0. The PEAR weights are redistributed under the upstream
+Apache-2.0 license of [BestWJH/PEAR_models](https://huggingface.co/BestWJH/PEAR_models) /
+[Pixel-Talk/PEAR](https://github.com/Pixel-Talk/PEAR). The SMPL-X / FLAME / MANO body models
+needed for mesh reconstruction are **not** included and carry their own restrictive licenses.
+
+## Citation
+
+    @misc{wu2026pear,
+      title         = {PEAR: Pixel-aligned Expressive humAn mesh Recovery},
+      author        = {Jiahao Wu and Yunfei Liu and Lijian Lin and Ye Zhu and Lei Zhu and Jingyi Li and Yu Li},
+      year          = {2026},
+      eprint        = {2601.22693},
+      archivePrefix = {arXiv},
+      primaryClass  = {cs.CV},
+      url           = {https://arxiv.org/abs/2601.22693}
+    }
+    @software{ib_robot,
+      title   = {IB-Robot: Intelligence Boom Robot},
+      url     = {https://atomgit.com/openeuler/IB_Robot},
+      license = {Apache-2.0}
+    }

artifacts/ascend_310p/pear_parameter_network_bs1.om

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67798d9f1da61fba4e5b706b20acf82cf2daf030a3239f89709e655421c84e81
+size 1358182285

assets/adapter.json

@@ -0,0 +1 @@
+{"interface":"tensor_model","family":"pear_parameter_network","model_type":"pear_parameter_network","operation":"predict_parameters","preprocessing":"pear-rgb-crop256-bgr-imagenet-v1","postprocessing":"pear-parameter-v1"}

assets/pear_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be82dfa06e7b0608c6440058dfa0794d9b2ceee69f6e5b09bf41bb0076abeb18
+size 2685908343

inference_manifest.json

@@ -0,0 +1,242 @@
+{
+  "schema_version": 3,
+  "bundle": {
+    "uuid": "ec439a1d-a65d-41fa-9d7c-47f81d07b09e",
+    "revision": 2,
+    "name": "pear_parameter_network",
+    "files": [
+      {
+        "path": "assets/adapter.json"
+      },
+      {
+        "path": "assets/pear_model.pt"
+      }
+    ],
+    "digest": {
+      "algorithm": "sha256",
+      "scope": "structure",
+      "value": "dd0291b4c5c6e734ac27aee60d4a0768bbd05c6109aefebfa33034b1fe095ca5"
+    }
+  },
+  "model": {
+    "interface": "tensor_model",
+    "model_type": "pear_parameter_network",
+    "operation": "predict_parameters",
+    "inputs": [
+      {
+        "semantic": "pear.input",
+        "dtype": "float32",
+        "layout": "NCHW",
+        "shape": [
+          1,
+          3,
+          256,
+          256
+        ]
+      }
+    ],
+    "outputs": [
+      {
+        "semantic": "smplx_pose_raw",
+        "dtype": "float32",
+        "shape": [
+          1,
+          312
+        ]
+      },
+      {
+        "semantic": "smplx_scale",
+        "dtype": "float32",
+        "shape": [
+          1,
+          6
+        ]
+      },
+      {
+        "semantic": "smplx_shape",
+        "dtype": "float32",
+        "shape": [
+          1,
+          200
+        ]
+      },
+      {
+        "semantic": "smplx_expression",
+        "dtype": "float32",
+        "shape": [
+          1,
+          50
+        ]
+      },
+      {
+        "semantic": "flame_pose",
+        "dtype": "float32",
+        "shape": [
+          1,
+          14
+        ]
+      },
+      {
+        "semantic": "flame_shape",
+        "dtype": "float32",
+        "shape": [
+          1,
+          300
+        ]
+      },
+      {
+        "semantic": "flame_expression",
+        "dtype": "float32",
+        "shape": [
+          1,
+          50
+        ]
+      },
+      {
+        "semantic": "camera_raw",
+        "dtype": "float32",
+        "shape": [
+          1,
+          3
+        ]
+      }
+    ],
+    "semantic_identity": {
+      "logical_model_revision": "pear-parameter-network@handoff",
+      "output_semantics": "pear-parameter-v1",
+      "preprocessing_contract": "pear-rgb-crop256-bgr-imagenet-v1"
+    }
+  },
+  "deployments": {
+    "ascend_310p": {
+      "uuid": "76c515a7-7460-4905-b847-562180448d06",
+      "revision": 1,
+      "artifacts": {
+        "model": {
+          "format": "om",
+          "path": "artifacts/ascend_310p/pear_parameter_network_bs1.om",
+          "sha256": "67798d9f1da61fba4e5b706b20acf82cf2daf030a3239f89709e655421c84e81"
+        }
+      },
+      "bindings": {
+        "model": {
+          "inputs": [
+            {
+              "semantic": "pear.input",
+              "runtime_name": "input",
+              "index": 0,
+              "dtype": "float32",
+              "layout": "NCHW",
+              "shape": [
+                1,
+                3,
+                256,
+                256
+              ]
+            }
+          ],
+          "outputs": [
+            {
+              "semantic": "smplx_pose_raw",
+              "runtime_name": "/Concat_1:0:smplx_pose_raw",
+              "index": 0,
+              "dtype": "float32",
+              "shape": [
+                1,
+                312
+              ]
+            },
+            {
+              "semantic": "smplx_scale",
+              "runtime_name": "PartitionedCall_/smplx_scale_decoder/Gemm_add_2114:0:smplx_scale",
+              "index": 1,
+              "dtype": "float32",
+              "shape": [
+                1,
+                6
+              ]
+            },
+            {
+              "semantic": "smplx_shape",
+              "runtime_name": "PartitionedCall_/smplx_shape_decoder/Gemm_add_2119:0:smplx_shape",
+              "index": 2,
+              "dtype": "float32",
+              "shape": [
+                1,
+                200
+              ]
+            },
+            {
+              "semantic": "smplx_expression",
+              "runtime_name": "PartitionedCall_/smplx_expression_decoder/Gemm_add_2124:0:smplx_expression",
+              "index": 3,
+              "dtype": "float32",
+              "shape": [
+                1,
+                50
+              ]
+            },
+            {
+              "semantic": "flame_pose",
+              "runtime_name": "PartitionedCall_/flame_poses_decoder/Gemm_add_2129:0:flame_pose",
+              "index": 4,
+              "dtype": "float32",
+              "shape": [
+                1,
+                14
+              ]
+            },
+            {
+              "semantic": "flame_shape",
+              "runtime_name": "PartitionedCall_/flame_shape_decoder/Gemm_add_2134:0:flame_shape",
+              "index": 5,
+              "dtype": "float32",
+              "shape": [
+                1,
+                300
+              ]
+            },
+            {
+              "semantic": "flame_expression",
+              "runtime_name": "PartitionedCall_/flame_expression_decoder/Gemm_add_2139:0:flame_expression",
+              "index": 6,
+              "dtype": "float32",
+              "shape": [
+                1,
+                50
+              ]
+            },
+            {
+              "semantic": "camera_raw",
+              "runtime_name": "PartitionedCall_/cam_decoder/Gemm_add_2144:0:camera_raw",
+              "index": 7,
+              "dtype": "float32",
+              "shape": [
+                1,
+                3
+              ]
+            }
+          ]
+        }
+      },
+      "execution": [
+        "model"
+      ],
+      "execution_contract": {
+        "state_scope": "request",
+        "execution_structure": "direct",
+        "cancellation_granularity": "request_boundary"
+      },
+      "runtime_profile": {
+        "backend": "ascend",
+        "target": {
+          "runtime": "acl",
+          "soc": "Ascend310P1"
+        },
+        "profile": {
+          "device_id": 0
+        }
+      }
+    }
+  }
+}