Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Marigold

Marigold

Reported on 28 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 Vision14 results

Depth EstimationonNYU-Depth V2
absolute relative error· uses extra data· 2023-12-04
0.055
best: 0.026 (HybridDepth)
SOTA
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonNYU-Depth V2
Delta < 1.25· uses extra data· 2023-12-04
0.964
best: 0.989 (UniK3D (FT, metric))
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2023-12-04
0.991
best: 1 (HybridDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2023-12-04
0.998
best: 1 (HybridDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonNYU-Depth V2
RMSE· uses extra data· 2023-12-04
0.224
best: 0.013 (Defocus/DepthNet (Normalized))
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonNYU-Depth V2
log 10· uses extra data· 2023-12-04
0.024
best: 0.059 (SC-DepthV2)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonETH3D
Delta < 1.25· 2023-12-04
0.096
best: 0.981 (Distill Any Depth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonETH3D
absolute relative error· 2023-12-04
0.065
best: 0.0121 (HDN)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonKITTI Eigen split
Delta < 1.25· uses extra data· 2023-12-04
0.916
best: 0.99 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2023-12-04
0.987
best: 0.999 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2023-12-04
0.996
best: 1 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonKITTI Eigen split
RMSE· uses extra data· 2023-12-04
3.304
best: 1.394 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonKITTI Eigen split
RMSE log· uses extra data· 2023-12-04
0.138
best: 0.048 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
Depth EstimationonKITTI Eigen split
absolute relative error· uses extra data· 2023-12-04
0.099
best: 0.029 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145

Methodology14 results

3DonNYU-Depth V2
absolute relative error· uses extra data· 2023-12-04
0.055
best: 0.026 (HybridDepth)
SOTA
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonNYU-Depth V2
Delta < 1.25· uses extra data· 2023-12-04
0.964
best: 0.989 (UniK3D (FT, metric))
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2023-12-04
0.991
best: 1 (HybridDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2023-12-04
0.998
best: 1 (HybridDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonNYU-Depth V2
RMSE· uses extra data· 2023-12-04
0.224
best: 0.013 (Defocus/DepthNet (Normalized))
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonNYU-Depth V2
log 10· uses extra data· 2023-12-04
0.024
best: 0.059 (SC-DepthV2)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonETH3D
Delta < 1.25· 2023-12-04
0.096
best: 0.981 (Distill Any Depth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonETH3D
absolute relative error· 2023-12-04
0.065
best: 0.0121 (HDN)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonKITTI Eigen split
Delta < 1.25· uses extra data· 2023-12-04
0.916
best: 0.99 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2023-12-04
0.987
best: 0.999 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2023-12-04
0.996
best: 1 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonKITTI Eigen split
RMSE· uses extra data· 2023-12-04
3.304
best: 1.394 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonKITTI Eigen split
RMSE log· uses extra data· 2023-12-04
0.138
best: 0.048 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145
3DonKITTI Eigen split
absolute relative error· uses extra data· 2023-12-04
0.099
best: 0.029 (SPIDepth)
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation arXiv:2312.02145