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/Gaming for Depth (GfD)

Gaming for Depth (GfD)

Reported on 12 benchmarks across 2 tasks

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

Computer Vision6 results

  • Depth EstimationonNYU-Depth V2
    Delta < 1.25· uses extra data
    0.931
    best: 0.989 (UniK3D (FT, metric))
  • Depth EstimationonNYU-Depth V2
    Delta < 1.25^2· uses extra data
    0.986
    best: 1 (HybridDepth)
  • Depth EstimationonNYU-Depth V2
    Delta < 1.25^3· uses extra data
    0.996
    best: 1 (HybridDepth)
  • Depth EstimationonNYU-Depth V2
    RMSE· uses extra data
    0.364
    best: 0.013 (Defocus/DepthNet (Normalized))
  • Depth EstimationonNYU-Depth V2
    absolute relative error· uses extra data
    0.08
    best: 0.026 (HybridDepth)
  • Depth EstimationonNYU-Depth V2
    log 10· uses extra data
    0.033
    best: 0.059 (SC-DepthV2)

Methodology6 results

  • 3DonNYU-Depth V2
    Delta < 1.25· uses extra data
    0.931
    best: 0.989 (UniK3D (FT, metric))
  • 3DonNYU-Depth V2
    Delta < 1.25^2· uses extra data
    0.986
    best: 1 (HybridDepth)
  • 3DonNYU-Depth V2
    Delta < 1.25^3· uses extra data
    0.996
    best: 1 (HybridDepth)
  • 3DonNYU-Depth V2
    RMSE· uses extra data
    0.364
    best: 0.013 (Defocus/DepthNet (Normalized))
  • 3DonNYU-Depth V2
    absolute relative error· uses extra data
    0.08
    best: 0.026 (HybridDepth)
  • 3DonNYU-Depth V2
    log 10· uses extra data
    0.033
    best: 0.059 (SC-DepthV2)