Metric3Dv2(g2, ZS)

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Computer Vision4 results

Surface Normals EstimationonIBims-1
% < 11.25· uses extra data· 2024-03-22
69.7
best: 69.9 (Marigold + E2E FT(zero-shot))
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonIBims-1
% < 22.5· uses extra data· 2024-03-22
76.2
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonIBims-1
% < 30· uses extra data· 2024-03-22
78.8
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonIBims-1
Mean· uses extra data· 2024-03-22
19.6
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506