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/SpinNet

SpinNet

Reported on 16 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision16 results

  • Point Cloud Registrationon3DMatch (trained on KITTI)
    Recall· 2020-11-24
    0.845
    best: 0.922 (GeDi)
    SOTA
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • Point Cloud RegistrationonETH (trained on 3DMatch)
    Recall (30cm, 5 degrees)· 2020-11-24
    73.07
    best: 94.25 (Exhaustive Grid Search)
    SOTA
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud Interpolationon3DMatch (trained on KITTI)
    Recall· 2020-11-24
    0.845
    best: 0.922 (GeDi)
    SOTA
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud InterpolationonETH (trained on 3DMatch)
    Recall (30cm, 5 degrees)· 2020-11-24
    73.07
    best: 94.25 (Exhaustive Grid Search)
    SOTA
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • Point Cloud RegistrationonKITTI (trained on 3DMatch)
    Success Rate· 2020-11-24
    81.44
    best: 98.92 (GeDi)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • Point Cloud RegistrationonETH (trained on 3DMatch)
    Feature Matching Recall· 2020-11-24
    0.928
    best: 0.982 (GeDi)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • Point Cloud RegistrationonKITTI
    Success Rate· 2020-11-24
    99.1
    best: 99.82 (GeDi)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • Point Cloud RegistrationonFPv1
    RRE (degrees)· 2020-11-24
    3.105
    best: 4.489 (FCGF + YOHO-O)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • Point Cloud RegistrationonFPv1
    RTE (cm)· 2020-11-24
    1.67
    best: 2.052 (DIP)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • Point Cloud RegistrationonFPv1
    Recall (3cm, 10 degrees)· 2020-11-24
    42.46
    best: 92.81 (Greedy Grid Search)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud InterpolationonKITTI (trained on 3DMatch)
    Success Rate· 2020-11-24
    81.44
    best: 98.92 (GeDi)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud InterpolationonETH (trained on 3DMatch)
    Feature Matching Recall· 2020-11-24
    0.928
    best: 0.982 (GeDi)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud InterpolationonKITTI
    Success Rate· 2020-11-24
    99.1
    best: 99.82 (GeDi)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud InterpolationonFPv1
    RRE (degrees)· 2020-11-24
    3.105
    best: 4.489 (FCGF + YOHO-O)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud InterpolationonFPv1
    RTE (cm)· 2020-11-24
    1.67
    best: 2.052 (DIP)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149
  • 3D Point Cloud InterpolationonFPv1
    Recall (3cm, 10 degrees)· 2020-11-24
    42.46
    best: 92.81 (Greedy Grid Search)
    SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationarXiv:2011.12149