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/SC-DepthV2

SC-DepthV2

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 Vision5 results

  • Depth EstimationonNYU-Depth V2
    log 10· 2020-06-04
    0.059
    SOTA
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • Depth EstimationonNYU-Depth V2
    Delta < 1.25· 2020-06-04
    0.82
    best: 0.989 (UniK3D (FT, metric))
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • Depth EstimationonNYU-Depth V2
    Delta < 1.25^2· 2020-06-04
    0.956
    best: 1 (HybridDepth)
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • Depth EstimationonNYU-Depth V2
    RMSE· 2020-06-04
    0.532
    best: 0.013 (Defocus/DepthNet (Normalized))
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • Depth EstimationonNYU-Depth V2
    absolute relative error· 2020-06-04
    0.138
    best: 0.026 (HybridDepth)
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708

Methodology5 results

  • 3DonNYU-Depth V2
    log 10· 2020-06-04
    0.059
    SOTA
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • 3DonNYU-Depth V2
    Delta < 1.25· 2020-06-04
    0.82
    best: 0.989 (UniK3D (FT, metric))
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • 3DonNYU-Depth V2
    Delta < 1.25^2· 2020-06-04
    0.956
    best: 1 (HybridDepth)
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • 3DonNYU-Depth V2
    RMSE· 2020-06-04
    0.532
    best: 0.013 (Defocus/DepthNet (Normalized))
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708
  • 3DonNYU-Depth V2
    absolute relative error· 2020-06-04
    0.138
    best: 0.026 (HybridDepth)
    Auto-Rectify Network for Unsupervised Indoor Depth EstimationarXiv:2006.02708