--- license: mit library_name: torch-pointcloud tags: - point-cloud - 3d - pytorch - torch-pointcloud - recon - classification datasets: - scanobjectnn base_model: torch-pointcloud/recon.pretrain.zekun-qi model-index: - name: recon.scanobjectnn-objonly.zekun-qi results: - task: type: point-cloud-classification dataset: name: ScanObjectNN (OBJ_ONLY) type: scanobjectnn metrics: - name: OA type: accuracy value: 93.63 - name: mAcc type: accuracy value: 93.74 --- # Model card for recon.scanobjectnn-objonly.zekun-qi A ReCon point cloud classification model (masked point transformer with cross-modal contrastive queries). Trained on ScanObjectNN (OBJ_ONLY). ## Model Details - **Model Type:** Point cloud classification - **Model Stats:** - Params (M): 43.6 - Classes: 15 - Features: 1536 - **Dataset:** ScanObjectNN (OBJ_ONLY) - **Metrics:** OA 93.63, mAcc 93.74 - **Paper:** [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://arxiv.org/abs/2302.02318) - **Converted from:** [qizekun/ReCon](https://github.com/qizekun/ReCon) (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( "recon.scanobjectnn-objonly.zekun-qi", 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), } data = collate([sample]) with torch.no_grad(): logits = model(data.get("x"), data["pos"], data["batch"]) ``` ## Feature extraction ```python with torch.no_grad(): embeddings = model.forward_features(data.get("x"), data["pos"], data["batch"]) model.reset_classifier(num_classes=0) with torch.no_grad(): embeddings = model(data.get("x"), data["pos"], data["batch"]) # (B, 1536) ``` ## Citation ```bibtex @inproceedings{qi2023recon, title = {Contrast with Reconstruct: Contrastive {3D} Representation Learning Guided by Generative Pretraining}, author = {Qi, Zekun and Dong, Runpei and Fan, Guofan and Ge, Zheng and Zhang, Xiangyu and Ma, Kaisheng and Yi, Li}, booktitle = {ICML}, year = {2023} } @inproceedings{uy2019scanobjectnn, title = {Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data}, author = {Mikaela Angelina Uy and Quang-Hieu Pham and Binh-Son Hua and Duc Thanh Nguyen and Sai-Kit Yeung}, booktitle = {ICCV}, year = {2019} } @software{dujardin2026pytorchpointcloud, author = {Arthur Dujardin}, title = {PyTorch PointCloud}, year = {2026}, doi = {10.5281/zenodo.22159632}, url = {https://github.com/arthurdjn/pytorch-pointcloud}, } ```