Point Cloud Registration On Fp O M
Metriken
RRE (degrees)
RTE (cm)
Recall (3cm, 10 degrees)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | RRE (degrees) | RTE (cm) | Recall (3cm, 10 degrees) | Paper Title | Repository |
|---|---|---|---|---|---|
| GeDi | 2.14 | 1.45 | 75.40 | Learning general and distinctive 3D local deep descriptors for point cloud registration | - |
| FCGF+SC2-PCR | 1.98 | 1.27 | 63.00 | SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration | - |
| FPFH+SC2-PCR | 1.68 | 0.80 | 84.70 | SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration | - |
| GO-ICP | - | - | 0.00 | Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration | - |
| GeoTransformer | 2.45 | 1.94 | 22.07 | GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer | - |
| Exhaustive Grid Search | 0.030 | 0.017 | 88.06 | Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark |
0 of 6 row(s) selected.