Research map / Point clouds / Point cloud classification
CloudMamba: Grouped Selective State Spaces for Point Cloud Analysis
Kanglin Qu, Pan Gao, Qun Dai, Zhanzhi Ye, Rui Ye, Yuanhao Sun
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add sorting prompt to each axis sequence (ablation) | CloudMamba · ModelNet40 | OA (%): 93.19 -> 93.65 | Improved |
| add position embedding (ablation) | CloudMamba · ModelNet40 | OA (%): 93.15 -> 93.65 | Improved |
| use GS6 (grouped parameter sharing) instead of S6 (ablation) | CloudMamba · ModelNet40 | OA (%): 92.11 -> 93.65 | Improved |
| use chained instead of parallel bidirectional Mamba (ablation) | CloudMamba · ModelNet40 | OA (%): 92.69 -> 93.65 | Improved |
| use sequence expanding & merging instead of Hilbert + Trans-Hilbert serialization (ablation) | CloudMamba · ModelNet40 | OA (%): 92.82 -> 93.65 | Improved |
| use all three axis sequences (X, Y, Z) instead of one (ablation) | CloudMamba · ModelNet40 | OA (%): 91.37 -> 93.65 | Improved |
| add causal axis sorting of points (ablation) | CloudMamba · ModelNet40 | OA (%): 88.98 -> 91.37 | Improved |
| CloudMamba vs pre-trained PointMamba on ScanObjectNN | CloudMamba · ScanObjectNN PB_T50_RS | OA (%): 89.3 -> 88.3 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Pamba — Pamba: Enhancing Global Interaction in Point Clouds via State Space Model (AAAI 2025) · better on 1 of 1 shared result
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
- Point Cloud Mamba: Point Cloud Learning via State Space Model (AAAI 2025 · similarity 0.93)
- PointMamba: A Simple State Space Model for Point Cloud Analysis (NeurIPS 2024 · similarity 0.92)
- Spectral Informed Mamba for Robust Point Cloud Processing (CVPR 2025 · similarity 0.90)
- Pamba: Enhancing Global Interaction in Point Clouds via State Space Model (AAAI 2025 · similarity 0.90)
- PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter (CVPR 2025 · similarity 0.87)
- ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding (NeurIPS 2025 · similarity 0.87)
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.
