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/NeWCRFs

NeWCRFs

Reported on 38 benchmarks across 2 tasks · 1 paper · 26 SOTA

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

Computer Vision19 results

Depth EstimationonNYU-Depth V2
Delta < 1.25· 2022-03-03
0.922
best: 0.989 (UniK3D (FT, metric))
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonNYU-Depth V2
Delta < 1.25^2· 2022-03-03
0.992
best: 1 (HybridDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· 2022-03-03
0.998
best: 1 (HybridDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonMatterport3D
Delta < 1.25· 2022-03-03
0.9376
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonMatterport3D
Delta < 1.25^2· 2022-03-03
0.9812
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonMatterport3D
Delta < 1.25^3· 2022-03-03
0.9933
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonMatterport3D
RMSE· 2022-03-03
0.4279
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonMatterport3D
absolute error· 2022-03-03
0.197
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonMatterport3D
absolute relative error· 2022-03-03
0.0793
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonKITTI Eigen split
Delta < 1.25· uses extra data· 2022-03-03
0.974
best: 0.99 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2022-03-03
0.997
best: 0.999 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonKITTI Eigen split
RMSE log· uses extra data· 2022-03-03
0.079
best: 0.048 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonKITTI Eigen split
absolute relative error· uses extra data· 2022-03-03
0.052
best: 0.029 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonNYU-Depth V2
RMSE· 2022-03-03
0.334
best: 0.013 (Defocus/DepthNet (Normalized))
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonNYU-Depth V2
absolute relative error· 2022-03-03
0.095
best: 0.026 (HybridDepth)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonNYU-Depth V2
log 10· 2022-03-03
0.041
best: 0.059 (SC-DepthV2)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2022-03-03
0.999
best: 1 (SPIDepth)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonKITTI Eigen split
RMSE· uses extra data· 2022-03-03
2.129
best: 1.394 (SPIDepth)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
Depth EstimationonKITTI Eigen split
Sq Rel· uses extra data· 2022-03-03
0.155
best: 0.224 (SfM-Revisited)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502

Methodology19 results

3DonNYU-Depth V2
Delta < 1.25· 2022-03-03
0.922
best: 0.989 (UniK3D (FT, metric))
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonNYU-Depth V2
Delta < 1.25^2· 2022-03-03
0.992
best: 1 (HybridDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonNYU-Depth V2
Delta < 1.25^3· 2022-03-03
0.998
best: 1 (HybridDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonMatterport3D
Delta < 1.25· 2022-03-03
0.9376
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonMatterport3D
Delta < 1.25^2· 2022-03-03
0.9812
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonMatterport3D
Delta < 1.25^3· 2022-03-03
0.9933
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonMatterport3D
RMSE· 2022-03-03
0.4279
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonMatterport3D
absolute error· 2022-03-03
0.197
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonMatterport3D
absolute relative error· 2022-03-03
0.0793
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonKITTI Eigen split
Delta < 1.25· uses extra data· 2022-03-03
0.974
best: 0.99 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonKITTI Eigen split
Delta < 1.25^2· uses extra data· 2022-03-03
0.997
best: 0.999 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonKITTI Eigen split
RMSE log· uses extra data· 2022-03-03
0.079
best: 0.048 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonKITTI Eigen split
absolute relative error· uses extra data· 2022-03-03
0.052
best: 0.029 (SPIDepth)
SOTA
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonNYU-Depth V2
RMSE· 2022-03-03
0.334
best: 0.013 (Defocus/DepthNet (Normalized))
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonNYU-Depth V2
absolute relative error· 2022-03-03
0.095
best: 0.026 (HybridDepth)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonNYU-Depth V2
log 10· 2022-03-03
0.041
best: 0.059 (SC-DepthV2)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonKITTI Eigen split
Delta < 1.25^3· uses extra data· 2022-03-03
0.999
best: 1 (SPIDepth)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonKITTI Eigen split
RMSE· uses extra data· 2022-03-03
2.129
best: 1.394 (SPIDepth)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502
3DonKITTI Eigen split
Sq Rel· uses extra data· 2022-03-03
0.155
best: 0.224 (SfM-Revisited)
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation arXiv:2203.01502