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/iDisc

iDisc

Reported on 25 benchmarks across 3 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 Vision15 results

  • Surface Normals EstimationonNYU Depth v2
    % < 11.25· 2023-04-13
    63.8
    best: 68.8 (Metric3Dv2(L, FT))
    SOTA
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Surface Normals EstimationonNYU Depth v2
    % < 22.5· 2023-04-13
    79.8
    best: 84.9 (Metric3Dv2(L, FT))
    SOTA
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Surface Normals EstimationonNYU Depth v2
    % < 30· 2023-04-13
    85.6
    best: 89.8 (Metric3Dv2(L, FT))
    SOTA
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Surface Normals EstimationonNYU Depth v2
    Mean Angle Error· 2023-04-13
    14.6
    best: 12 (Metric3Dv2(L, FT))
    SOTA
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonNYU-Depth V2
    Delta < 1.25^2· 2023-04-13
    0.993
    best: 1 (HybridDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonNYU-Depth V2
    Delta < 1.25^3· 2023-04-13
    0.999
    best: 1 (HybridDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonNYU-Depth V2
    absolute relative error· 2023-04-13
    0.086
    best: 0.026 (HybridDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonKITTI Eigen split
    Delta < 1.25· 2023-04-13
    0.977
    best: 0.99 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonKITTI Eigen split
    Delta < 1.25^2· 2023-04-13
    0.997
    best: 0.999 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonKITTI Eigen split
    Delta < 1.25^3· 2023-04-13
    0.999
    best: 1 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonKITTI Eigen split
    RMSE· 2023-04-13
    2.067
    best: 1.394 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonKITTI Eigen split
    RMSE log· 2023-04-13
    0.077
    best: 0.048 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonKITTI Eigen split
    Sq Rel· 2023-04-13
    0.145
    best: 0.224 (SfM-Revisited)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Depth EstimationonKITTI Eigen split
    absolute relative error· 2023-04-13
    0.05
    best: 0.029 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • Surface Normals EstimationonNYU Depth v2
    RMSE· 2023-04-13
    22.8
    best: 19.2 (Metric3Dv2(L, FT))
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334

Methodology10 results

  • 3DonNYU-Depth V2
    Delta < 1.25^2· 2023-04-13
    0.993
    best: 1 (HybridDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonNYU-Depth V2
    Delta < 1.25^3· 2023-04-13
    0.999
    best: 1 (HybridDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonNYU-Depth V2
    absolute relative error· 2023-04-13
    0.086
    best: 0.026 (HybridDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonKITTI Eigen split
    Delta < 1.25· 2023-04-13
    0.977
    best: 0.99 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonKITTI Eigen split
    Delta < 1.25^2· 2023-04-13
    0.997
    best: 0.999 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonKITTI Eigen split
    Delta < 1.25^3· 2023-04-13
    0.999
    best: 1 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonKITTI Eigen split
    RMSE· 2023-04-13
    2.067
    best: 1.394 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonKITTI Eigen split
    RMSE log· 2023-04-13
    0.077
    best: 0.048 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonKITTI Eigen split
    Sq Rel· 2023-04-13
    0.145
    best: 0.224 (SfM-Revisited)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334
  • 3DonKITTI Eigen split
    absolute relative error· 2023-04-13
    0.05
    best: 0.029 (SPIDepth)
    iDisc: Internal Discretization for Monocular Depth EstimationarXiv:2304.06334