FPFH

Reported on 6 benchmarks across 2 tasks

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

Computer Vision6 results

Point Cloud Registrationon3DMatch (trained on KITTI)
Recall
0.136
best: 0.922 (GeDi)
Point Cloud RegistrationonETH (trained on 3DMatch)
Feature Matching Recall
0.221
best: 0.982 (GeDi)
Point Cloud RegistrationonETH (trained on 3DMatch)
Recall (30cm, 5 degrees)
66.34
best: 94.25 (Exhaustive Grid Search)
3D Point Cloud Interpolationon3DMatch (trained on KITTI)
Recall
0.136
best: 0.922 (GeDi)
3D Point Cloud InterpolationonETH (trained on 3DMatch)
Feature Matching Recall
0.221
best: 0.982 (GeDi)
3D Point Cloud InterpolationonETH (trained on 3DMatch)
Recall (30cm, 5 degrees)
66.34
best: 94.25 (Exhaustive Grid Search)