Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/FCGF

FCGF

Reported on 15 benchmarks across 3 tasks

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

Computer Vision14 results

Point Cloud Registrationon3DMatch (trained on KITTI)
Recall
0.325
best: 0.922 (GeDi)
Point Cloud RegistrationonKITTI (trained on 3DMatch)
Success Rate
24.19
best: 98.92 (GeDi)
Point Cloud RegistrationonKITTI (FCGF setting)
Recall (0.6m, 5 degrees)
98.2
best: 99.5 (GeoTransformer)
Point Cloud RegistrationonETH (trained on 3DMatch)
Feature Matching Recall
0.161
best: 0.982 (GeDi)
Point Cloud RegistrationonKITTI
Success Rate
96.57
best: 99.82 (GeDi)
Point Cloud RegistrationonRotKITTI Registration Benchmark
RR@(1,0.1)
3.6
best: 73.3 (UMERegRobust)
Point Cloud RegistrationonRotKITTI Registration Benchmark
RR@(1.5,0.3)
11.6
best: 81.1 (UMERegRobust)
3D Point Cloud Interpolationon3DMatch (trained on KITTI)
Recall
0.325
best: 0.922 (GeDi)
3D Point Cloud InterpolationonKITTI (trained on 3DMatch)
Success Rate
24.19
best: 98.92 (GeDi)
3D Point Cloud InterpolationonKITTI (FCGF setting)
Recall (0.6m, 5 degrees)
98.2
best: 99.5 (GeoTransformer)
3D Point Cloud InterpolationonETH (trained on 3DMatch)
Feature Matching Recall
0.161
best: 0.982 (GeDi)
3D Point Cloud InterpolationonKITTI
Success Rate
96.57
best: 99.82 (GeDi)
3D Point Cloud InterpolationonRotKITTI Registration Benchmark
RR@(1,0.1)
3.6
best: 73.3 (UMERegRobust)
3D Point Cloud InterpolationonRotKITTI Registration Benchmark
RR@(1.5,0.3)
11.6
best: 81.1 (UMERegRobust)

Methodology1 result

3Don3DMatch Benchmark
Average Recall
0.9578