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/Metric3Dv2(L, FT)

Metric3Dv2(L, FT)

Reported on 17 benchmarks across 3 tasks · 1 paper · 9 SOTA

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

Computer Vision11 results

Depth EstimationonNYU-Depth V2
Delta < 1.25· uses extra data· 2024-03-22
0.989
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Depth EstimationonNYU-Depth V2
absolute relative error· uses extra data· 2024-03-22
0.047
best: 0.026 (HybridDepth)
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonNYU Depth v2
% < 11.25· uses extra data· 2024-03-22
68.8
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonNYU Depth v2
% < 22.5· uses extra data· 2024-03-22
84.9
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonNYU Depth v2
% < 30· uses extra data· 2024-03-22
89.8
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonNYU Depth v2
Mean Angle Error· uses extra data· 2024-03-22
12
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonNYU Depth v2
RMSE· uses extra data· 2024-03-22
19.2
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Depth EstimationonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2024-03-22
0.998
best: 1 (HybridDepth)
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Depth EstimationonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2024-03-22
1
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Depth EstimationonNYU-Depth V2
RMSE· uses extra data· 2024-03-22
0.183
best: 0.013 (Defocus/DepthNet (Normalized))
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Depth EstimationonNYU-Depth V2
log 10· uses extra data· 2024-03-22
0.02
best: 0.059 (SC-DepthV2)
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506

Methodology6 results

3DonNYU-Depth V2
Delta < 1.25· uses extra data· 2024-03-22
0.989
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
3DonNYU-Depth V2
absolute relative error· uses extra data· 2024-03-22
0.047
best: 0.026 (HybridDepth)
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
3DonNYU-Depth V2
Delta < 1.25^2· uses extra data· 2024-03-22
0.998
best: 1 (HybridDepth)
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
3DonNYU-Depth V2
Delta < 1.25^3· uses extra data· 2024-03-22
1
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
3DonNYU-Depth V2
RMSE· uses extra data· 2024-03-22
0.183
best: 0.013 (Defocus/DepthNet (Normalized))
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
3DonNYU-Depth V2
log 10· uses extra data· 2024-03-22
0.02
best: 0.059 (SC-DepthV2)
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506