Point Cloud Registration On Rotkitti
Metrics
RR@(1,0.1)
RR@(1.5,0.3)
Results
Performance results of various models on this benchmark
Model Name | RR@(1,0.1) | RR@(1.5,0.3) | Paper Title | Repository |
|---|---|---|---|---|
| GCL | 28.8 | 40.1 | Density-invariant Features for Distant Point Cloud Registration | |
| GeoTransformer | 50.1 | 78.5 | GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer | |
| FCGF | 3.6 | 11.6 | Fully Convolutional Geometric Features | |
| CoFiNet | 30.1 | 62.5 | CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration | |
| UMERegRobust | 73.3 | 81.1 | UMERegRobust -- Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration | - |
| PREDATOR | 35.0 | 41.6 | PREDATOR: Registration of 3D Point Clouds with Low Overlap |
0 of 6 row(s) selected.