Papers › Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled...

Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models

1 Jan 2025CVPR 2025 1archive 2025-07-28

Jiuming Liu, Jinru Han, Lihao Liu, Angelica I. Aviles-Rivero, Chaokang Jiang, Zhe Liu, Hesheng Wang

Point cloud videos can faithfully capture real-world spatial geometries and temporal dynamics, which are essential for enabling intelligent agents to understand the dynamically changing world. However, designing an effective 4D backbone remains challenging, mainly due to the irregular and unordered distribution of points and temporal inconsistencies across frames. Also, recent transformer-based 4D backbones commonly suffer from large computational costs due to their quadratic complexity, particularly for long video sequences. To address these challenges, we propose a novel point cloud video understanding backbone purely based on the State Space Models (SSMs). Specifically, we first disentangle space and time in 4D video sequences and then establish the spatio-temporal correlation with the unified spatial-temporal Mamba blocks. The Intra-frame Spatial Mamba module is developed to encode locally similar geometric structures within a certain temporal stride. Subsequently, locally correlated tokens are delivered to the Inter-frame Temporal Mamba module, which integrates long-term point features across the entire video with linear complexity. Our proposed Mamba4D achieves competitive performance on the MSR-Action3D action recognition (+10.4% accuracy), HOI4D action segmentation (+0.7 F1 Score), and Synthia4D semantic segmentation (+0.19 mIoU) datasets. Mamba4D also has a significant efficiency improvement, especially for long video sequences, with 87.5% GPU memory reduction and 5.36 times speed-up. Codes are released at https://github.com/IRMVLab/Mamba4D.

PaperPDFCode

Code

irmvlab/mamba4d officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionAction SegmentationMambaSemantic SegmentationState Space ModelsVideo Understandingpoint cloud video understanding

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Mamba

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections