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/NgeNet

NgeNet

Reported on 10 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision10 results

  • Point Cloud Registrationon3DMatch (at least 30% overlapped - FCGF setting)
    Recall (0.3m, 15 degrees)· 2022-01-28
    95
    SOTA
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • 3D Point Cloud Interpolationon3DMatch (at least 30% overlapped - FCGF setting)
    Recall (0.3m, 15 degrees)· 2022-01-28
    95
    SOTA
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • Point Cloud Registrationon3DLoMatch (10-30% overlap)
    Recall ( correspondence RMSE below 0.2)· 2022-01-28
    71.9
    best: 8.4 (OMNet (reported in REGTR))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • Point Cloud Registrationon3DMatch (at least 30% overlapped - FCGF setting)
    RE (all)· 2022-01-28
    4.932
    best: 9.8 (PCAM-Soft (All post-processing))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • Point Cloud Registrationon3DMatch (at least 30% overlapped - FCGF setting)
    TE (all)· 2022-01-28
    0.155
    best: 0.25 (DGR (RE (all), TE(all) are reported in PCAM))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • Point Cloud Registrationon3DMatch (at least 30% overlapped - sample 5k interest points)
    Recall ( correspondence RMSE below 0.2)· 2022-01-28
    92.9
    best: 35.9 (OMNet (reported in REGTR))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • 3D Point Cloud Interpolationon3DLoMatch (10-30% overlap)
    Recall ( correspondence RMSE below 0.2)· 2022-01-28
    71.9
    best: 8.4 (OMNet (reported in REGTR))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • 3D Point Cloud Interpolationon3DMatch (at least 30% overlapped - FCGF setting)
    RE (all)· 2022-01-28
    4.932
    best: 9.8 (PCAM-Soft (All post-processing))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • 3D Point Cloud Interpolationon3DMatch (at least 30% overlapped - FCGF setting)
    TE (all)· 2022-01-28
    0.155
    best: 0.25 (DGR (RE (all), TE(all) are reported in PCAM))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094
  • 3D Point Cloud Interpolationon3DMatch (at least 30% overlapped - sample 5k interest points)
    Recall ( correspondence RMSE below 0.2)· 2022-01-28
    92.9
    best: 35.9 (OMNet (reported in REGTR))
    Leveraging Inlier Correspondences Proportion for Point Cloud RegistrationarXiv:2201.12094