Awesome

<div align="center">

Point Cloud Mamba: Point Cloud Learning via State Space Model

Tao Zhang, Xiangtai Li*, Haobo Yuan, Shunping Ji, Shuicheng Yan

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

News

All codes and weights are available.

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.

Install

See Installation Instructions.

Getting Started

See Preparing Datasets for PCM.

See Getting Started with PCM.

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 Li, Xiangtai and Yuan, Haobo and Ji, Shunping and Yan, Shuicheng},
  journal={arXiv preprint arXiv:2403.00762},
  year={2024}
}

Acknowledgement

This repo is based on PointNeXt, PointMLP, Mamba, Vim, and Pontcept. Thanks for their excellent works.