Research map / Point clouds / Registration and matching
End-to-End Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration
Read the paperCheck 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 |
|---|---|---|---|
| Apply S2H matching to DCP | DCP · ModelNet40 clean and noisy | RMSE(R): 6.265 -> 2.522 (clean); 6.347 -> 3.886 (noisy) | Helped |
| Apply S2H matching to RPMNet | RPMNet · ModelNet40 clean and noisy | RMSE(R): 0.886 -> 0.514 (clean); 1.631 -> 1.456 (noisy) | Helped |
| Apply S2H matching to DGR | DGR · 3DMatch | RE (deg): 2.43 -> 1.75 | Helped |
| Apply S2H matching to DGR | DGR · KITTI | Recall (%): 96.9 -> 99.3 | Helped |
| Replace post-processing with end-to-end S2H learning (ablation) | SHM_DCP · ModelNet40 clean | RMSE(R): 3.325 -> 2.522 | Helped |
| Replace post-processing with end-to-end S2H learning (ablation) | SHM_DCP · ModelNet40 noisy | RMSE(R): 4.570 -> 3.886 | Helped |
Closest papers by meaning
- Implicit Correspondence Learning for Image-to-Point Cloud Registration (CVPR 2025 · similarity 0.88)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.87)
- PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration (AAAI 2025 · similarity 0.87)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.87)
- APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction (NeurIPS 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.