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/Marigold + E2E FT(zero-shot)

Marigold + E2E FT(zero-shot)

Reported on 8 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Computer Vision6 results

  • Surface Normals EstimationonIBims-1
    % < 11.25· 2024-09-17
    69.9
    SOTA
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355
  • Depth EstimationonNYU-Depth V2
    Delta < 1.25· 2024-09-17
    0.966
    best: 0.989 (UniK3D (FT, metric))
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355
  • Depth EstimationonNYU-Depth V2
    absolute relative error· 2024-09-17
    0.052
    best: 0.026 (HybridDepth)
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355
  • Surface Normals EstimationonIBims-1
    Mean· 2024-09-17
    15.8
    best: 19.6 (Metric3Dv2(g2, ZS))
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355
  • Surface Normals EstimationonNYU Depth v2
    % < 11.25· 2024-09-17
    61.4
    best: 68.8 (Metric3Dv2(L, FT))
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355
  • Surface Normals EstimationonNYU Depth v2
    Mean Angle Error· 2024-09-17
    16.2
    best: 12 (Metric3Dv2(L, FT))
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355

Methodology2 results

  • 3DonNYU-Depth V2
    Delta < 1.25· 2024-09-17
    0.966
    best: 0.989 (UniK3D (FT, metric))
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355
  • 3DonNYU-Depth V2
    absolute relative error· 2024-09-17
    0.052
    best: 0.026 (HybridDepth)
    Fine-Tuning Image-Conditional Diffusion Models is Easier than You ThinkarXiv:2409.11355