Research map / Point clouds / Point cloud classification
Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understanding
Jincen Jiang, Qianyu Zhou, Yuhang Li, Kui Su, Meili Wang, Jian Chang, Jian Jun Zhang, Xuequan Lu
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 |
|---|---|---|---|
| replace Transformer in DG-PIC with Mamba using coordinate serialization (vanilla Mamba ICL) | DG-PIC · MP3DObject | reconstruction CD: 5.91 -> 8.28 | Hurt |
| add structure-aware serialization and hierarchical domain-aware modeling to Mamba ICL | vanilla Mamba ICL · MP3DObject | reconstruction CD: 8.28 -> 3.55 | Improved |
| use CDS+GCS structure-aware serialization instead of Z-order scanning (ablation) | SADG · MP3DObject | reconstruction CD: 7.32 -> 3.55 | Improved |
| use CDS+GCS serialization instead of Hilbert curve (ablation) | SADG · MP3DObject | registration CD: 7.68 -> 2.84 | Improved |
| add Centroid Distance Spectrum serialization (ablation) | SADG · MP3DObject | denoising CD: 10.69 -> 6.61 | Improved |
| add Geodesic Curvature Spectrum serialization (ablation) | SADG · MP3DObject | reconstruction CD: 5.82 -> 3.55 | Improved |
| add intra-domain structural modeling (ISM) (ablation) | SADG HDM · MP3DObject | denoising CD: 11.37 -> 6.61 | Improved |
| add inter-domain relational fusion (IRF) with interleaving (ablation) | SADG HDM · MP3DObject | reconstruction CD: 6.92 -> 3.55 | Improved |
| replace DG-PIC Transformer with SADG Mamba | DG-PIC · efficiency | inference time: 0.94s -> 0.75s | Improved |
| SADG vs DG-PIC on ScanObjectNN reconstruction | SADG · ScanObjectNN | reconstruction CD: 4.52 -> 4.29 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DG-PIC — DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding (ECCV 2024) · better on 8 of 8 shared results
- PointDGMamba — PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model (AAAI 2025) · better on 1 of 1 shared result
- PointMamba — PointMamba: A Simple State Space Model for Point Cloud Analysis (NeurIPS 2024) · 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 0.88)
- Spectral Informed Mamba for Robust Point Cloud Processing (CVPR 2025 · similarity 0.88)
- PointMamba: A Simple State Space Model for Point Cloud Analysis (NeurIPS 2024 · similarity 0.87)
- PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model (AAAI 2025 · similarity 0.87)
- PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter (CVPR 2025 · similarity 0.86)
- DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion (AAAI 2025 · similarity 0.86)
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.
