| --- |
| license: mit |
| library_name: torch-pointcloud |
| tags: |
| - point-cloud |
| - 3d |
| - pytorch |
| - torch-pointcloud |
| - litept |
| - segmentation |
| datasets: |
| - structured3d |
| --- |
| |
| # Model card for litept-large.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): 85.9 |
| - 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-large.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}, |
| } |
| ``` |
|
|
