Update README.md and config.json and model.safetensors for litept-base.structured3d.prs-eth

README.md

@@ -0,0 +1,106 @@
+---
+license: mit
+library_name: torch-pointcloud
+tags:
+- point-cloud
+- 3d
+- pytorch
+- torch-pointcloud
+- litept
+- segmentation
+datasets:
+- structured3d
+---
+
+# Model card for litept-base.structured3d.prs-eth
+
+A LitePT point cloud semantic segmentation model (convolutions in the early stages, attention with 3D rotary embedding in the late ones). Trained on Structured3D.
+
+## Model Details
+
+- **Model Type:** Point cloud semantic segmentation
+- **Model Stats:**
+  - Params (M): 45.1
+  - Input channels: 6
+  - Classes: 25
+  - Features: 72
+- **Dataset:** Structured3D
+- **Paper:** [LitePT: Lighter Yet Stronger Point Transformer](https://arxiv.org/abs/2512.13689)
+- **Converted from:** [prs-eth/LitePT](https://github.com/prs-eth/LitePT) (MIT)
+- **Library:** [torch-pointcloud](https://github.com/arthurdjn/pytorch-pointcloud)
+
+## Install
+
+```bash
+pip install torch-pointcloud
+```
+
+This checkpoint also needs `spconv` and `flash-attn`, which need a build matching your torch and CUDA: see the [installation guide](https://pytorch-pointcloud.org/latest/installation/).
+
+## Usage
+
+```python
+import torch
+import torch_pointcloud as tp
+from torch_pointcloud.utils.data import collate
+
+model, info = tp.create_model(
+    "litept-base.structured3d.prs-eth",
+    pretrained=True,
+    return_info=True,
+)
+model = model.cuda().eval()  # GPU-only kernels
+
+# synthetic sample with the keys a dataset provides
+num_points = 8192
+sample = {
+    "pos": torch.randn(num_points, 3),
+    "color": torch.rand(num_points, 3) * 255,
+    "normal": torch.randn(num_points, 3),
+    "segment": torch.zeros(num_points, dtype=torch.long),
+    "instance": torch.zeros(num_points, dtype=torch.long),
+}
+data = info["transform"](sample)
+data = collate([data])
+data = {key: value.cuda() for key, value in data.items()}
+
+with torch.no_grad():
+    logits = model(data.get("x"), data["pos_grid"], data["batch"])
+```
+
+## Feature extraction
+
+```python
+with torch.no_grad():
+    features = model.forward_features(data.get("x"), data["pos_grid"], data["batch"])
+
+model.reset_classifier(num_classes=0)
+with torch.no_grad():
+    features = model(data.get("x"), data["pos_grid"], data["batch"])  # (N, 72)
+```
+
+## Citation
+
+```bibtex
+@inproceedings{yue2026litept,
+  title   = {LitePT: Lighter Yet Stronger Point Transformer},
+  author  = {Yuanwen Yue and Damien Robert and Jianyuan Wang and Sunghwan Hong and Jan Dirk Wegner and Christian Rupprecht and Konrad Schindler},
+  booktitle = {CVPR},
+  year    = {2026}
+}
+
+@inproceedings{zheng2020structured3d,
+  title   = {Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling},
+  author  = {Jia Zheng and Junfei Zhang and Jing Li and Rui Tang and Shenghua Gao and Zihan Zhou},
+  booktitle = {ECCV},
+  year    = {2020}
+}
+
+@software{dujardin2026pytorchpointcloud,
+  author  = {Arthur Dujardin},
+  title   = {PyTorch PointCloud},
+  year    = {2026},
+  doi     = {10.5281/zenodo.22159632},
+  url     = {https://github.com/arthurdjn/pytorch-pointcloud},
+}
+```

config.json

@@ -0,0 +1,145 @@
+{
+  "library_name": "torch-pointcloud",
+  "name": "litept-base.structured3d.prs-eth",
+  "task": "semantic-segmentation",
+  "hparams": {
+    "in_channels": 6,
+    "num_classes": 25,
+    "serialization_orders": [
+      "z",
+      "z-trans",
+      "hilbert",
+      "hilbert-trans"
+    ],
+    "shuffle_serialization_orders": true,
+    "strides": [
+      2,
+      2,
+      2,
+      2
+    ],
+    "encoder_depths": [
+      3,
+      3,
+      3,
+      12,
+      3
+    ],
+    "encoder_channels": [
+      54,
+      108,
+      216,
+      432,
+      576
+    ],
+    "encoder_num_heads": [
+      3,
+      6,
+      12,
+      24,
+      32
+    ],
+    "encoder_patch_size": [
+      1024,
+      1024,
+      1024,
+      1024,
+      1024
+    ],
+    "encoder_conv": [
+      true,
+      true,
+      true,
+      false,
+      false
+    ],
+    "encoder_attention": [
+      false,
+      false,
+      false,
+      true,
+      true
+    ],
+    "decoder_depths": [
+      0,
+      0,
+      0,
+      0
+    ],
+    "decoder_channels": [
+      432,
+      216,
+      108,
+      72
+    ],
+    "decoder_num_heads": [
+      24,
+      12,
+      6,
+      4
+    ],
+    "decoder_patch_size": [
+      1024,
+      1024,
+      1024,
+      1024
+    ],
+    "decoder_conv": [
+      false,
+      false,
+      false,
+      false
+    ],
+    "decoder_attention": [
+      false,
+      false,
+      false,
+      false
+    ],
+    "norm": "batch_norm",
+    "norm_kwargs": {
+      "eps": 0.001,
+      "momentum": 0.01
+    },
+    "act": "gelu",
+    "mlp_ratio": 4.0,
+    "drop_path": 0.3,
+    "rope_base": 100.0,
+    "use_flash_attn": true
+  },
+  "input_keys": [
+    "x",
+    "pos_grid",
+    "batch"
+  ],
+  "dataset": "structured3d",
+  "classes": [
+    "wall",
+    "floor",
+    "cabinet",
+    "bed",
+    "chair",
+    "sofa",
+    "table",
+    "door",
+    "window",
+    "picture",
+    "desk",
+    "shelves",
+    "curtain",
+    "dresser",
+    "pillow",
+    "mirror",
+    "ceiling",
+    "refrigerator",
+    "television",
+    "nightstand",
+    "sink",
+    "lamp",
+    "otherstructure",
+    "otherfurniture",
+    "otherprop"
+  ],
+  "author": "prs-eth",
+  "license": "MIT"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33efe6ca7dc4a67d2bd11a427477fb17c138e19ecb4f86282fdf0514511dc8cf
+size 180523592