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

Source: [Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy](<https://www.sota2.com/research/paper/68fa72951e209131cea574d7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:31:06.454Z

Authors: Jiuming Liu, Ruiji Yu, Yian Wang, Yu Zheng, Tianchen Deng, Weicai Ye, Hesheng Wang

Published: 2024-03-11T07:07:39.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Classification on ModelNet40 (Overall Accuracy)](<https://www.sota2.com/research/sota/object-classification-on-modelnet40-overall-accuracy.md>): Object Classification; ModelNet40; Overall Accuracy: 93.4.

- [Semantic Segmentation on ScanNet v2 (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-scannet-v2-val.md>): Semantic segmentation; ScanNet V2 (val); mIoU: 74.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.06467>)

[PDF](<https://arxiv.org/pdf/2403.06467.pdf>)
