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/StrutDepth

StrutDepth

Reported on 10 benchmarks across 2 tasks · 1 paper

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 self-supervised
    Absolute relative error (AbsRel)· 2021-08-19
    0.142
    best: 0.126 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • Depth EstimationonNYU-Depth V2 self-supervised
    Root mean square error (RMSE)· 2021-08-19
    0.54
    best: 0.494 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • Depth EstimationonNYU-Depth V2 self-supervised
    delta_1· 2021-08-19
    81.3
    best: 84.5 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • Depth EstimationonNYU-Depth V2 self-supervised
    delta_2· 2021-08-19
    95.4
    best: 96.5 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • Depth EstimationonNYU-Depth V2 self-supervised
    delta_3· 2021-08-19
    98.8
    best: 99.1 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574

Methodology5 results

  • 3DonNYU-Depth V2 self-supervised
    Absolute relative error (AbsRel)· 2021-08-19
    0.142
    best: 0.126 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • 3DonNYU-Depth V2 self-supervised
    Root mean square error (RMSE)· 2021-08-19
    0.54
    best: 0.494 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • 3DonNYU-Depth V2 self-supervised
    delta_1· 2021-08-19
    81.3
    best: 84.5 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • 3DonNYU-Depth V2 self-supervised
    delta_2· 2021-08-19
    95.4
    best: 96.5 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574
  • 3DonNYU-Depth V2 self-supervised
    delta_3· 2021-08-19
    98.8
    best: 99.1 (IndoorDepth)
    StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationarXiv:2108.08574