In this work, for the first time, we demonstrate that Mamba-based point cloud methods can outperform point-based methods. Mamba exhibits strong global modeling capabilities and linear computational complexity, making it highly attractive for point cloud analysis. To enable more effective processing of 3-D point cloud data by Mamba, we propose a novel Consistent Traverse Serialization to convert point clouds into 1-D point sequences while ensuring that neighboring points in the sequence are also spatially adjacent. Consistent Traverse Serialization yields six variants by permuting the order of x, y, and z coordinates, and the synergistic use of these variants aids Mamba in comprehensively observing point cloud data. Furthermore, to assist Mamba in handling point sequences with different orders more effectively, we introduce point prompts to inform Mamba of the sequence's arrangement rules. Finally, we propose positional encoding based on spatial coordinate mapping to inject positional information into point cloud sequences better. Based on these improvements, we construct a point cloud network named Point Cloud Mamba, which combines local and global modeling. Point Cloud Mamba surpasses the SOTA point-based method PointNeXt and achieves new SOTA performance on the ScanObjectNN, ModelNet40, and ShapeNetPart datasets.

本研究首次展示了基于Mamba的点云方法能够超越基于点的方法，Mamba具备强大的全局建模能力和线性计算复杂度，对点云分析非常具有吸引力。为了更有效地处理3D点云数据，我们提出了一种新颖的一致遍历序列化方法，将点云转换为1D点序列，并确保序列中相邻的点也是空间上相邻的。一致遍历序列化方法通过排列x、y和z坐标的顺序产生六种变体，通过这些变体的协同使用，有助于Mamba全面观察点云数据。此外，为了更有效地帮助Mamba处理不同顺序的点序列，我们引入了点提示的概念，以告知Mamba序列的排列规则。最后，我们提出了基于空间坐标映射的位置编码方法，更好地将位置信息注入点云序列中。基于这些改进，我们构建了一种名为Point Cloud Mamba的点云网络，它结合了局部建模和全局建模。Point Cloud Mamba超越了SOTA方法PointNeXt，并在ScanObjectNN、ModelNet40和ShapeNetPart数据集上取得了新的SOTA性能。

点云蟒蛇：基于状态空间模型的点云学习