PointMamba: A Simple State Space Model for Point Cloud Analysis
read the original abstract
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}.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
SUMO: Segment and Track Any Motion with Nonlinear State Space Models
SUMO is a training-free unified framework using nonlinear SSM and Selective Unscented Filter for VOT and MOS, reporting SOTA results.
-
SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning
SFMambaNet combines a Local Spectral-Geometric Attention block with a Spectral-Integrated Global Mamba block to improve inlier-outlier separation in two-view correspondence pruning.
-
3DTMDet: A Dual-Path Synergy Network of Transformer and SSM for 3D Object Detection in Point Clouds
3DTMDet proposes a hybrid Mamba-Transformer architecture with a 3DHMT block and LiDAR-inspired voxel generation to improve 3D object detection in point clouds, outperforming prior methods on KITTI and ONCE datasets.
-
EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond
EventCrab integrates frame and point networks with a joint representation space, SCL, and Hilbert-scan EPE to improve event-based action recognition by 5-7% on two datasets.
-
3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion
3DMambaComplete applies the Mamba model to point cloud completion via hyperpoint generation, spatial spreading, and mesh deformation, claiming better results than prior methods on benchmarks.
-
A Survey of Mamba
The paper consolidates existing research on Mamba models, their architecture variants, adaptations to different data modalities, and applications across domains.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.