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。