Metric3Dv2 (g2, In-domain)

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 EstimationonScanNetV2
% < 11.25· uses extra data· 2024-03-22
77.8
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonScanNetV2
% < 22.5· uses extra data· 2024-03-22
90.1
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonScanNetV2
% < 30· uses extra data· 2024-03-22
93.5
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506
Surface Normals EstimationonScanNetV2
Mean Angle Error· uses extra data· 2024-03-22
9.2
SOTA
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation arXiv:2404.15506