Research map / Point clouds / Registration and matching
Robust Point Cloud Registration Framework Based on Deep Graph Matching
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use deep graph matching to incorporate graph structure and topology into point correspondences | RGM · ModelNet40 clean point clouds | registration error | Helped |
| use deep graph matching to incorporate graph structure and topology into point correspondences | RGM · ModelNet40 Gaussian noise | recall | Helped |
| use deep graph matching to incorporate graph structure and topology into point correspondences | RGM · ModelNet40 partial-to-partial | registration error | Helped |
| use deep graph matching to incorporate graph structure and topology into point correspondences | RGM · ModelNet40 unseen categories | registration performance | Helped |
| replace AIS with L2 node-feature distances transformed by an exponential and Sinkhorn (ablation) | RGM · ModelNet40 partial-to-partial | registration accuracy | Hurt |
| replace transformer-generated edges with full-connection edges (ablation) | RGM · ModelNet40 partial-to-partial | registration performance | Hurt |
Closest papers by meaning
- GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning (CVPR 2025 · similarity 0.91)
- PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques (ICML 2024 · similarity 0.90)
- A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration (NeurIPS 2024 · similarity 0.89)
- 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration (NeurIPS 2024 · similarity 0.89)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.89)
- SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks (CVPR 2024 · similarity 0.89)
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.