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 this https URL

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

Point Mamba: A Novel Point Cloud Backbone Based on State Space Model  with Octree-Based Ordering Strategy

Transformers have been essential to pretraining success in NLP. Other
architectures have been used, but require attention layers to match benchmark
accuracy. This work explores pretraining without attention. We test recently
developed routing layers based on state-space models (SSM) and model
architectures based on multiplicative gating. Used together these modeling
choices have a large impact on pretraining accuracy. Empirically the proposed
Bidirectional Gated SSM (BiGS) replicates BERT pretraining results without
attention and can be extended to long-form pretraining of 4096 tokens without
approximation.

研究探索了基于状态空间模型的路由层和基于乘性门控机制的模型架构并结合使用对预训练准确性有很大的影响，提出的双向门控 SSM 模型可以在没有注意机制的情况下复现 BERT 的预训练结果，并可扩展到预训练 4096 个令牌。