point-mae-base.scanobjectnn-objonly.yatian-pang

Model card for point-mae-base.scanobjectnn-objonly.yatian-pang

A Point-MAE point cloud classification model (masked point autoencoder). Trained on ScanObjectNN (OBJ_ONLY).

Model Details

• Model Type: Point cloud classification
• Model Stats:
  • Params (M): 22.1
  • Classes: 15
  • Features: 768
• Dataset: ScanObjectNN (OBJ_ONLY)
• Metrics: OA 88.3, mAcc 87.09 (reference 88.29)
• Paper: Masked Autoencoders for Point Cloud Self-supervised Learning
• Converted from: Pang-Yatian/Point-MAE (MIT)
• 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(
    "point-mae-base.scanobjectnn-objonly.yatian-pang",
    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

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, 768)

Citation

@inproceedings{pang2022pointmae,
  title   = {Masked Autoencoders for Point Cloud Self-supervised Learning},
  author  = {Yatian Pang and Wenxiao Wang and Francis E. H. Tay and Wei Liu and Yonghong Tian and Li Yuan},
  booktitle = {ECCV},
  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},
}