Methods › Computer Vision › Point Cloud Models › RPM-Net
RPM-Net
Introduced by Zi Jian Yew et al. in RPM-Net: Robust Point Matching using Learned Features
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
RPM-Net is an end-to-end differentiable deep network for robust point matching uses learned features. It preserves robustness of RPM against noisy/outlier points while desensitizing initialization with point correspondences from learned feature distances instead of spatial distances. The network uses the differentiable Sinkhorn layer and annealing to get soft assignments of point correspondences from hybrid features learned from both spatial coordinates and local geometry. To further improve registration performance, the authors introduce a secondary network to predict optimal annealing parameters.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registration 6 May 2021 · 0 repositories · arXiv:2105.02714
-
RPM-Net: Robust Point Matching using Learned Features 30 Mar 2020 · 5 repositories · arXiv:2003.13479Syntology ran 6 of 31 samples · 25 unverified · 14 pointer-only (licence)
Tasks archive 2025-07-28
2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Deep Learning | 1 |
| Point Cloud Registration | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections