PointMamba: A Simple State Space Model for Point Cloud Analysis

By Dingkang Liang, Xin Zhou, Wei Xu, Xingkui Zhu, Zhikang Zou, Xiaoqing Ye, Xiao Tan, Xiang Bai. Neural Information Processing Systems, 2024

328 citations recorded by the source corpus.

Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity method with global modeling appealing. In this paper, we propose PointMamba, transferring the success of Mamba, a recent representative state space model (SSM), from NLP to point cloud analysis tasks. Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs. Specifically, our method leverages space-filling curves for effective point tokenization and adopts an extremely simple, non-hierarchical Mamba encoder as the backbone. Comprehensive evaluations demonstrate that PointMamba achieves superior performance across multiple datasets while significantly reducing GPU memory usage and FLOPs. This work underscores the potential of SSMs in 3D vision-related tasks and presents a simple yet effective Mamba-based baseline for future research. The code will be made available at \url{https://github.com/LMD0311/PointMamba}.

Subfields: Computational Mechanics, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/21ddc4fc3551619b8a64db6ae124acc72aaae2c2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

Citations in the corpus

Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, neutral): “Recently, to achieve model scalability, Transformers-based (e.g., PointTransformer [78], Swin3d [79], PT2 [80], 3D-VisTA [81], LEO [82], PQ3D [83]) and Mamba-based (e.g., PointMamba [84], Mamba3D [85]) architectures have emerged.”
MambaHSI: Spatial–Spectral Mamba for Hyperspectral Image Classification (2025, background): “…from the strong long-range modeling capabilities while maintaining linear computational complexity, the Mamba has received substantial research across many fields, such as language understanding [22], [24], medical image analysis [17], [25], computer vision [19], [26], and so on [27], [28], [29].”
VideoMamba: State Space Model for Efficient Video Understanding (2024, neutral): “Mamba’s potential has motivated a series of works [11,28,30, 32, 46, 50, 56, 79, 80, 88, 91], demonstrating better performance and higher GPU e ﬃ ciency than Transformers on visual tasks like object detection and semantic segmentation.”