Research map / Point clouds / Registration and matching
RPM-Net: Robust Point Matching Using Learned Features
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 learned hybrid features and Sinkhorn-based outlier handling | RPM-Net · ModelNet40 Gaussian noise | isotropic rotation error: 0.664 vs 2.926 | Helped |
| Use learned hybrid features and Sinkhorn-based outlier handling | RPM-Net · ModelNet40 partial visibility with noise | isotropic rotation error: 1.712 vs 6.380 | Helped |
| Remove PPF features (ablation) | RPM-Net · ModelNet40 partial visibility with noise | isotropic rotation error: 1.712 -> 3.302 | Hurt |
| Remove local neighbor coordinates Δx (ablation) | RPM-Net · ModelNet40 partial visibility with noise | isotropic rotation error: 1.712 -> 2.781 | Hurt |
| Remove absolute centroid coordinates x (ablation) | RPM-Net · ModelNet40 partial visibility with noise | isotropic rotation error: 1.712 -> 5.501 | Hurt |
| Replace per-iteration parameter prediction with fixed learned α and β (ablation) | RPM-Net · ModelNet40 partial visibility with noise | isotropic rotation error: 1.712 -> 2.220 | Hurt |
Closest papers by meaning
- Robust Point Cloud Registration Framework Based on Deep Graph Matching (CVPR 2021 · similarity 0.90)
- End-to-End Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration (AAAI 2022 · similarity 0.89)
- PointDSC: Robust Point Cloud Registration Using Deep Spatial Consistency (CVPR 2021 · similarity 0.89)
- Implicit Correspondence Learning for Image-to-Point Cloud Registration (CVPR 2025 · similarity 0.88)
- HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration (CVPR 2025 · similarity 0.87)
- Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment (AAAI 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.
