List your company

SVBRDF Multi-view Consistency on 5 synthetic scenes (test)

0.056Basecolor ConsistencyUNet-HF
0.0470.107750.16850.22925Dec 15, 2025

Evaluation results

MethodLinks
UNet-HFInput modalities=RGB, normals, and depth maps, Model Category=Regression2025.120.0560.050.04133,534
UNet-HFInput modalities=Training without normals and depth maps, Model Category=Regression2025.120.060.0640.04840,912
UNet-RGBInput modalities=RGB, normals, and depth maps, Model Category=Regression2025.120.0640.0780.06361
GenPerceptInput modalities=RGB, normals, and depth maps, Model Category=Regression2025.120.0720.1040.069694
Zeng et al.Model Category=Regression, Citation=[ZLH*22]2025.120.0730.10.105415
GenPerceptInput modalities=Training without normals and depth maps, Model Category=Regression2025.120.0750.1080.069742
UNet-RGBInput modalities=Training without normals and depth maps, Model Category=Regression2025.120.0890.1170.077362
Kocsis et al.Number of predictions averaged (xN)=10, Model Category=Generative2025.120.1240.10.104—
Zeng et al.Model Category=Generative, Citation=[ZDG*24]2025.120.1550.2470.542—
Kocsis et al.Number of predictions averaged (xN)=1, Model Category=Generative2025.120.2810.2270.2196