Recently, state space model (SSM) has gained great attention due to its promising performance, linear complexity, and long sequence modeling ability in both language and image domains. However, it is non-trivial to extend SSM to the point cloud field, because of the causality requirement of SSM and the disorder and irregularity nature of point clouds. In this paper, we propose a novel SSM-based point cloud processing backbone, named Point Mamba, with a causality-aware ordering mechanism. To construct the causal dependency relationship, we design an octree-based ordering strategy on raw irregular points, globally sorting points in a z-order sequence and also retaining their spatial proximity. Our method achieves state-of-the-art performance compared with transformer-based counterparts, with 93.4% accuracy and 75.7 mIOU respectively on the ModelNet40 classification dataset and ScanNet semantic segmentation dataset. Furthermore, our Point Mamba has linear complexity, which is more efficient than transformer-based methods. Our method demonstrates the great potential that SSM can serve as a generic backbone in point cloud understanding. Codes are released at https://github.com/IRMVLab/Point-Mamba.

提出了一种基于SSM的点云处理骨干网络Point Mamba，具有因果感知的排序机制，在构建因果依赖关系方面采用基于八叉树的排序策略，通过全局排序点以Z序列并保留它们的空间接近度。与基于transformer的对应方法相比，我们的方法在ModelNet40分类数据集和ScanNet语义分割数据集上分别达到了93.4％的准确率和75.7的mIOU，且Point Mamba具有线性复杂度，比基于transformer的方法更高效。这表明SSM在点云理解中具有巨大潜力。

Point Mamba：基于状态空间模型的新型点云骨干网络与八叉树排序策略