AI Paper Atlas

Research map / Point clouds / Point cloud classification

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning

Chuxin Wang, Yixin Zha, Wenfei Yang, Tianzhu Zhang

ICCV 2025 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add structural SSM block to standard Mamba baseline (ablation)Mamba baseline · ScanObjectNN PB-T50-RSaccuracy: 87.23 -> 92.09Improved
add structural SSM block to standard Mamba baseline (ablation)Mamba baseline · ModelNet40accuracy: 91.86 -> 94.45Improved
add sequence length-adaptive strategy (ablation)StruMamba3D · ScanObjectNN PB-T50-RSaccuracy: 92.09 -> 92.75Improved
add state-wise update (MLP of relative offsets) on top of spatial states (ablation)Structural SSM · ScanObjectNN PB-T50-RSaccuracy: 91.33 -> 92.75Improved
add spatial state initialization alone (no state-wise update) (ablation)Mamba with phi(x) · ScanObjectNN PB-T50-RSaccuracy: 90.94 -> 91.33No clear effect
generate SSM parameters from spatial offsets only, dropping point-feature term (ablation)Structural SSM · ScanObjectNN PB-T50-RSaccuracy: 92.75 -> 91.12Hurt
add adaptive state update mechanism alone (ablation)Pre-training · ScanObjectNN PB-T50-RSaccuracy: 92.09 -> 92.26No clear effect
add both ASUM and spatial state consistency loss (lambda=2) (ablation)Pre-training · ScanObjectNN PB-T50-RSaccuracy: 92.09 -> 92.75Improved
raise consistency loss weight lambda from 2 to 5 (ablation)Pre-training · ScanObjectNN PB-T50-RSaccuracy: 92.75 -> 92.57Hurt
add lightweight convolution for spatial states (ablation)Structural SSM block · ScanObjectNN PB-T50-RSaccuracy: 91.78 -> 92.22Improved
add bidirectional scanning (ablation)Structural SSM block · ModelNet40accuracy: 94.81 -> 95.06Improved
add Hilbert serialization to StruMamba3D (ablation)StruMamba3D · ScanObjectNN PB-T50-RSaccuracy: 92.75 -> 92.81No clear effect

Later papers that compared with this method

1 later accepted paper reports StruMamba3D as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy