TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/GeDi

GeDi

Reported on 64 benchmarks across 2 tasks · 1 paper · 60 SOTA

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

Computer Vision64 results

  • Point Cloud Registrationon3DMatch (trained on KITTI)
    Recall· 2021-05-21
    0.922
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-E
    RRE (degrees)· 2021-05-21
    1.629
    best: 2.29 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-E
    RTE (cm)· 2021-05-21
    1.162
    best: 1.57 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-E
    Recall (3cm, 10 degrees)· 2021-05-21
    99.76
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-H
    RRE (degrees)· 2021-05-21
    1.7
    best: 1.77 (FCGF+SC2-PCR )
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-H
    RTE (cm)· 2021-05-21
    1.63
    best: 1.69 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-H
    Recall (3cm, 10 degrees)· 2021-05-21
    99.41
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonKITTI (trained on 3DMatch)
    Success Rate· 2021-05-21
    98.92
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-M
    RRE (degrees)· 2021-05-21
    2.14
    best: 2.45 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-M
    RTE (cm)· 2021-05-21
    1.45
    best: 1.94 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-M
    Recall (3cm, 10 degrees)· 2021-05-21
    75.4
    best: 88.06 (Exhaustive Grid Search)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-E
    RRE (degrees)· 2021-05-21
    1.69
    best: 2.3 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-E
    RTE (cm)· 2021-05-21
    1.16
    best: 1.57 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-E
    Recall (3cm, 10 degrees)· 2021-05-21
    99.64
    best: 99.88 (FPFH+SC2-PCR )
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonETH (trained on 3DMatch)
    Feature Matching Recall· 2021-05-21
    0.982
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonETH (trained on 3DMatch)
    Recall (30cm, 5 degrees)· 2021-05-21
    86.54
    best: 94.25 (Exhaustive Grid Search)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-M
    RRE (degrees)· 2021-05-21
    1.65
    best: 2.29 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-M
    RTE (cm)· 2021-05-21
    1.15
    best: 1.58 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-M
    Recall (3cm, 10 degrees)· 2021-05-21
    99.7
    best: 99.82 (Exhaustive Grid Search)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-E
    RRE (degrees)· 2021-05-21
    1.68
    best: 2.32 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-E
    RTE (cm)· 2021-05-21
    1.16
    best: 1.59 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-E
    Recall (3cm, 10 degrees)· 2021-05-21
    99.47
    best: 99.76 (FPFH+SC2-PCR)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-M
    Recall (3cm, 10 degrees)· 2021-05-21
    99.94
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonKITTI
    Success Rate· 2021-05-21
    99.82
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-H
    RRE (degrees)· 2021-05-21
    1.63
    best: 2.27 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-H
    RTE (cm)· 2021-05-21
    1.14
    best: 1.57 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-T-H
    Recall (3cm, 10 degrees)· 2021-05-21
    99.7
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-H
    RRE (degrees)· 2021-05-21
    2.56
    best: 2.68 (FCGF+SC2-PCR)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-H
    RTE (cm)· 2021-05-21
    1.76
    best: 2.22 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-O-H
    Recall (3cm, 10 degrees)· 2021-05-21
    8.7
    best: 38.85 (FPFH+SC2-PCR)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud Interpolationon3DMatch (trained on KITTI)
    Recall· 2021-05-21
    0.922
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-E
    RRE (degrees)· 2021-05-21
    1.629
    best: 2.29 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-E
    RTE (cm)· 2021-05-21
    1.162
    best: 1.57 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-E
    Recall (3cm, 10 degrees)· 2021-05-21
    99.76
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-H
    RRE (degrees)· 2021-05-21
    1.7
    best: 1.77 (FCGF+SC2-PCR )
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-H
    RTE (cm)· 2021-05-21
    1.63
    best: 1.69 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-H
    Recall (3cm, 10 degrees)· 2021-05-21
    99.41
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonKITTI (trained on 3DMatch)
    Success Rate· 2021-05-21
    98.92
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-M
    RRE (degrees)· 2021-05-21
    2.14
    best: 2.45 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-M
    RTE (cm)· 2021-05-21
    1.45
    best: 1.94 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-M
    Recall (3cm, 10 degrees)· 2021-05-21
    75.4
    best: 88.06 (Exhaustive Grid Search)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-E
    RRE (degrees)· 2021-05-21
    1.69
    best: 2.3 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-E
    RTE (cm)· 2021-05-21
    1.16
    best: 1.57 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-E
    Recall (3cm, 10 degrees)· 2021-05-21
    99.64
    best: 99.88 (FPFH+SC2-PCR )
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonETH (trained on 3DMatch)
    Feature Matching Recall· 2021-05-21
    0.982
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonETH (trained on 3DMatch)
    Recall (30cm, 5 degrees)· 2021-05-21
    86.54
    best: 94.25 (Exhaustive Grid Search)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-M
    RRE (degrees)· 2021-05-21
    1.65
    best: 2.29 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-M
    RTE (cm)· 2021-05-21
    1.15
    best: 1.58 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-M
    Recall (3cm, 10 degrees)· 2021-05-21
    99.7
    best: 99.82 (Exhaustive Grid Search)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-E
    RRE (degrees)· 2021-05-21
    1.68
    best: 2.32 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-E
    RTE (cm)· 2021-05-21
    1.16
    best: 1.59 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-E
    Recall (3cm, 10 degrees)· 2021-05-21
    99.47
    best: 99.76 (FPFH+SC2-PCR)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-M
    Recall (3cm, 10 degrees)· 2021-05-21
    99.94
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonKITTI
    Success Rate· 2021-05-21
    99.82
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-H
    RRE (degrees)· 2021-05-21
    1.63
    best: 2.27 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-H
    RTE (cm)· 2021-05-21
    1.14
    best: 1.57 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-T-H
    Recall (3cm, 10 degrees)· 2021-05-21
    99.7
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-H
    RRE (degrees)· 2021-05-21
    2.56
    best: 2.68 (FCGF+SC2-PCR)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-H
    RTE (cm)· 2021-05-21
    1.76
    best: 2.22 (GeoTransformer)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-O-H
    Recall (3cm, 10 degrees)· 2021-05-21
    8.7
    best: 38.85 (FPFH+SC2-PCR)
    SOTA
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-M
    RRE (degrees)· 2021-05-21
    1.66
    best: 2.26 (GeoTransformer)
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • Point Cloud RegistrationonFP-R-M
    RTE (cm)· 2021-05-21
    1.14
    best: 2.71 (GO-ICP)
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-M
    RRE (degrees)· 2021-05-21
    1.66
    best: 2.26 (GeoTransformer)
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382
  • 3D Point Cloud InterpolationonFP-R-M
    RTE (cm)· 2021-05-21
    1.14
    best: 2.71 (GO-ICP)
    Learning general and distinctive 3D local deep descriptors for point cloud registrationarXiv:2105.10382