| --- |
| license: mit |
| library_name: torch-pointcloud |
| tags: |
| - point-cloud |
| - 3d |
| - pytorch |
| - torch-pointcloud |
| - pointnet2 |
| - segmentation |
| datasets: |
| - s3dis |
| model-index: |
| - name: pointnet2.s3dis-area2.openpoints |
| results: |
| - task: |
| type: point-cloud-segmentation |
| dataset: |
| name: S3DIS (Area 2) |
| type: s3dis |
| metrics: |
| - name: mIoU |
| type: mean_iou |
| value: 48.31 |
| - name: OA |
| type: accuracy |
| value: 80.14 |
| --- |
| |
| # Model card for pointnet2.s3dis-area2.openpoints |
|
|
| A PointNet++ point cloud semantic segmentation model (hierarchical set abstraction). Trained on S3DIS (Area 2). |
|
|
| ## Model Details |
|
|
| - **Model Type:** Point cloud semantic segmentation |
| - **Model Stats:** |
| - Params (M): 1.0 |
| - Input channels: 4 |
| - Classes: 13 |
| - Features: 128 |
| - **Dataset:** S3DIS (Area 2) |
| - **Metrics:** mIoU 48.31, OA 80.14 |
| - **Paper:** [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://arxiv.org/abs/1706.02413) |
| - **Converted from:** [guochengqian/PointNeXt](https://github.com/guochengqian/PointNeXt) (MIT) |
| - **Library:** [torch-pointcloud](https://github.com/arthurdjn/pytorch-pointcloud) |
|
|
| ## Install |
|
|
| ```bash |
| pip install torch-pointcloud |
| ``` |
|
|
| ## Usage |
|
|
| ```python |
| import torch |
| import torch_pointcloud as tp |
| from torch_pointcloud.utils.data import collate |
| |
| model, info = tp.create_model( |
| "pointnet2.s3dis-area2.openpoints", |
| pretrained=True, |
| return_info=True, |
| ) |
| model = model.eval() |
| |
| # 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, |
| } |
| data = info["transform"](sample) |
| data = collate([data]) |
| |
| with torch.no_grad(): |
| logits = model(data.get("x"), data["pos"], data["batch"]) |
| ``` |
|
|
| ## Feature extraction |
|
|
| ```python |
| with torch.no_grad(): |
| features = model.forward_features(data.get("x"), data["pos"], data["batch"]) |
| |
| model.reset_classifier(num_classes=0) |
| with torch.no_grad(): |
| features = model(data.get("x"), data["pos"], data["batch"]) # (N, 128) |
| ``` |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{qi2017pointnet2, |
| title = {PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space}, |
| author = {Charles R. Qi and Li Yi and Hao Su and Leonidas J. Guibas}, |
| booktitle = {NeurIPS}, |
| year = {2017} |
| } |
| |
| @inproceedings{armeni2016s3dis, |
| title = {{3D} Semantic Parsing of Large-Scale Indoor Spaces}, |
| author = {Armeni, Iro and Sener, Ozan and Zamir, Amir R. and Jiang, Helen and Brilakis, Ioannis and Fischer, Martin and Savarese, Silvio}, |
| booktitle = {CVPR}, |
| year = {2016} |
| } |
| |
| @software{dujardin2026pytorchpointcloud, |
| author = {Arthur Dujardin}, |
| title = {PyTorch PointCloud}, |
| year = {2026}, |
| doi = {10.5281/zenodo.22159632}, |
| url = {https://github.com/arthurdjn/pytorch-pointcloud}, |
| } |
| ``` |
|
|
