Model card for point-mamba-base.pretrain.dingkang-liang
A PointMamba self-supervised pretraining model (state space model over serialized points). Pretrained on ShapeNet-55.
Model Details
- Model Type: Self-supervised pretraining
- Model Stats:
- Params (M): 16.1
- Dataset: ShapeNet-55
- Paper: PointMamba: A Simple State Space Model for Point Cloud Analysis
- Converted from: LMD0311/PointMamba (Apache-2.0)
- Library: torch-pointcloud
Install
pip install torch-pointcloud
This checkpoint also needs mamba-ssm, which needs a build matching your torch and CUDA: see the installation guide.
Usage
import torch
import torch_pointcloud as tp
from torch_pointcloud.utils.data import collate
model, info = tp.create_model(
"point-mamba-base.pretrain.dingkang-liang",
pretrained=True,
return_info=True,
)
model = model.cuda().eval() # GPU-only kernels
# synthetic sample with the keys a dataset provides
num_points = 8192
sample = {
"pos": torch.randn(num_points, 3),
}
data = collate([sample])
data = {key: value.cuda() for key, value in data.items()}
with torch.no_grad():
out = model(data.get("x"), data["pos"], data["batch"])
Citation
@inproceedings{liang2024pointmamba,
title = {PointMamba: A Simple State Space Model for Point Cloud Analysis},
author = {Dingkang Liang and Xin Zhou and Wei Xu and Xingkui Zhu and Zhikang Zou and Xiaoqing Ye and Xiao Tan and Xiang Bai},
booktitle = {NeurIPS},
year = {2024}
}
@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},
}