CoFF

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Point Cloud Registrationon3DLoMatch (10-30% overlap)
Recall ( correspondence RMSE below 0.2)· 2025-05-19
81.6
best: 8.4 (OMNet (reported in REGTR))
Cross-modal feature fusion for robust point cloud registration with ambiguous geometry arXiv:2505.13088
Point Cloud RegistrationonScanNet++ (trained on 3DMatch)
Recall ( correspondence RMSE below 0.2)· 2025-05-19
78.7
best: 63.7 (Predator)
Cross-modal feature fusion for robust point cloud registration with ambiguous geometry arXiv:2505.13088
3D Point Cloud Interpolationon3DLoMatch (10-30% overlap)
Recall ( correspondence RMSE below 0.2)· 2025-05-19
81.6
best: 8.4 (OMNet (reported in REGTR))
Cross-modal feature fusion for robust point cloud registration with ambiguous geometry arXiv:2505.13088
3D Point Cloud InterpolationonScanNet++ (trained on 3DMatch)
Recall ( correspondence RMSE below 0.2)· 2025-05-19
78.7
best: 63.7 (Predator)
Cross-modal feature fusion for robust point cloud registration with ambiguous geometry arXiv:2505.13088