Model card for point-bert-base.dvae.xumin-yu

A Point-BERT self-supervised pretraining model (masked point modeling transformer). Pretrained on ShapeNet-55.

Model Details

• Model Type: Self-supervised pretraining
• Model Stats:
  • Params (M): 27.6
• Dataset: ShapeNet-55
• Paper: Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
• Converted from: Julie-tang00/Point-BERT (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-bert-base.dvae.xumin-yu",
    task="base",
    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():
    out = model(data.get("x"), data["pos"], data["batch"])

Citation

@inproceedings{yu2022pointbert,
  title   = {Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling},
  author  = {Xumin Yu and Lulu Tang and Yongming Rao and Tiejun Huang and Jie Zhou and Jiwen Lu},
  booktitle = {CVPR},
  year    = {2022}
}

@article{chang2015shapenet,
  author  = {Chang, Angel X. and Funkhouser, Thomas and Guibas, Leonidas and Hanrahan, Pat and Huang, Qixing and Li, Zimo and Savarese, Silvio and Savva, Manolis and Song, Shuran and Su, Hao and Xiao, Jianxiong and Yi, Li and Yu, Fisher},
  title   = {{ShapeNet}: An Information-Rich {3D} Model Repository},
  journal = {arXiv preprint arXiv:1512.03012},
  year    = {2015},
}

@software{dujardin2026pytorchpointcloud,
  author  = {Arthur Dujardin},
  title   = {PyTorch PointCloud},
  year    = {2026},
  doi     = {10.5281/zenodo.22159632},
  url     = {https://github.com/arthurdjn/pytorch-pointcloud},
}