Awesome

<div align="center">

Point Cloud Mamba: Point Cloud Learning via State Space Model

Tao Zhang, Haobo Yuan, Lu Qi, Jiangning Zhang, Qianyu Zhou, Shunping Ji, Shuicheng Yan, Xiangtai Li

</div>

News

PCM is finally accepted by AAAI-2025.
All codes and weights are available at SkyworkAI/PointCloudMamba.

<div align="center"> <img src="https://github.com/zhang-tao-whu/paper_images/blob/master/pcm/pcm-idea.png" width="800"/> </div>

Features

PCM introduces Mamba to point cloud analysis.
PCM can perform global modeling while maintaining linear computational complexity.
PCM outperforms PointNeXt on the ScanObjectNN, ModelNet40, and ShapeNetPart datasets.

Demos

ShapeNetPart

<img src="https://github.com/zhang-tao-whu/paper_images/blob/master/pcm/pcm-demo.png" width="800"/>

Performance

3-D Point Cloud Classification

<img src="https://github.com/zhang-tao-whu/paper_images/blob/master/pcm/pcm-exp-1.png" width="600"/>

3-D Point Cloud Segmentation

<img src="https://github.com/zhang-tao-whu/paper_images/blob/master/pcm/pcm-exp-2.png" width="500"/>

@article{zhang2024point,
  title={Point Cloud Mamba: Point Cloud Learning via State Space Model},
  author={Zhang, Tao and Yuan, Haobo and Qi, Lu and Zhanng, Jiangning and Zhou, Qianyu and Ji, Shunping and Yan, Shuicheng and Li, Xiangtai},
  journal={AAAI},
  year={2025}
}

License

MIT License