README.md

metadata

license: apache-2.0
library_name: torch-pointcloud
tags:
  - point-cloud
  - 3d
  - pytorch
  - torch-pointcloud
  - pointmlp
  - classification
datasets:
  - scanobjectnn
model-index:
  - name: pointmlp-base.scanobjectnn.xu-ma
    results:
      - task:
          type: point-cloud-classification
        dataset:
          name: ScanObjectNN
          type: scanobjectnn
        metrics:
          - name: OA
            type: accuracy
            value: 77.48

Model card for pointmlp-base.scanobjectnn.xu-ma

A PointMLP point cloud classification model (residual MLP with geometric affine grouping). Trained on ScanObjectNN.

Model Details

• Model Type: Point cloud classification
• Model Stats:
  • Params (M): 13.2
  • Input channels: 3
  • Classes: 15
  • Features: 1024
• Dataset: ScanObjectNN
• Metrics: OA 77.48 (reference 86.1)
• Paper: Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
• Converted from: ma-xu/pointMLP-pytorch (Apache-2.0)
• Library: torch-pointcloud

Install

pip install torch-pointcloud

Usage

import torch
import torch_pointcloud as tp
from torch_pointcloud.utils.data import collate

model, info = tp.create_model(
    "pointmlp-base.scanobjectnn.xu-ma",
    task="classification",
    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),
    "normal": torch.randn(num_points, 3),
}
data = info["transform"](sample)
data = collate([data])

with torch.no_grad():
    logits = model(data.get("x"), data["pos"], data["batch"])

Feature extraction

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, 1024)

Citation

@inproceedings{ma2022pointmlp,
  title   = {Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework},
  author  = {Xu Ma and Can Qin and Haoxuan You and Haoxi Ran and Yun Fu},
  booktitle = {ICLR},
  year    = {2022}
}

@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},
}