Model card for point-m2ae-base.pretrain.renrui-zhang

A Point-M2AE self-supervised pretraining model (multi-scale masked autoencoder). Pretrained on ShapeNet-55.

Model Details

• Model Type: Self-supervised pretraining
• Model Stats:
  • Params (M): 15.3
• Dataset: ShapeNet-55
• Paper: Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
• Converted from: ZrrSkywalker/Point-M2AE (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-m2ae-base.pretrain.renrui-zhang",
    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{zhang2022pointm2ae,
  title   = {Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training},
  author  = {Renrui Zhang and Ziyu Guo and Rongyao Fang and Bin Zhao and Dong Wang and Yu Qiao and Hongsheng Li and Peng Gao},
  booktitle = {NeurIPS},
  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},
}