Papers › PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
Anh-Quan Cao, Gilles Puy, Alexandre Boulch, Renaud Marlet
Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering these correspondences to keep only the most reliable ones to estimate the transformation. Recently, several deep nets have been proposed to solve these steps jointly. We built upon these works and propose PCAM: a neural network whose key element is a pointwise product of cross-attention matrices that permits to mix both low-level geometric and high-level contextual information to find point correspondences. These cross-attention matrices also permits the exchange of context information between the point clouds, at each layer, allowing the network construct better matching features within the overlapping regions. The experiments show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets. Our code and trained models are available at https://github.com/valeoai/PCAM.
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Point Cloud Registration | 3DLoMatch (10-30% overlap) | PCAM (reported in REGTR) | Recall ( correspondence RMSE below 0.2) | 54.9 | #7 of 13 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | PCAM-Sparse (All post-processing) | RE (all) | 8.9 | #3 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | PCAM-Sparse (All post-processing) | Recall (0.3m, 15 degrees) | 92.4 | #3 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | PCAM-Sparse (All post-processing) | TE (all) | 0.23 | #3 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | PCAM-Soft (All post-processing) | RE (all) | 9.8 | #5 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | PCAM-Soft (All post-processing) | Recall (0.3m, 15 degrees) | 91.3 | #5 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - FCGF setting) | PCAM-Soft (All post-processing) | TE (all) | 0.24 | #5 of 14 | Archive leaderboard | report |
| Point Cloud Registration | 3DMatch (at least 30% overlapped - sample 5k interest points) | PCAM (reported in REGTR) | Recall ( correspondence RMSE below 0.2) | 85.5 | #5 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-soft + ICP | RE (all) | 0.79 | #4 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-soft + ICP | Recall (0.6m, 5 degrees) | 98 | #4 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-soft + ICP | TE (all) | 0.12 | #4 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-Sparse + ICP | RE (all) | 1.04 | #5 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-Sparse + ICP | Recall (0.6m, 5 degrees) | 97.4 | #5 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-Sparse + ICP | TE (all) | 0.17 | #5 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM - Soft | RE (all) | 1.00 | #6 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM - Soft | Recall (0.6m, 5 degrees) | 97.2 | #6 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM - Soft | TE (all) | 0.18 | #6 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-Sparse | RE (all) | 1.17 | #8 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-Sparse | Recall (0.6m, 5 degrees) | 96.5 | #8 of 11 | Archive leaderboard | report |
| Point Cloud Registration | KITTI (FCGF setting) | PCAM-Sparse | TE (all) | 0.22 | #8 of 11 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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