List your company
ResearchFormerly WizWand

Monocular Depth Estimation on KITTI-360 (test)

2.04RMSEUniDepth + Calibration Tokens
1.89462.876053.85754.83895Aug 6, 2025
Updated 7mo ago

Evaluation results

MethodLinks
UniDepth + Calibration TokensExperiment=+ Calibration Tokens, Model=UniDepth, Train Dataset=Mix 200K, Zero-shot=true2025.082.0466.4
DepthAnything + Calibration TokensExperiment=+ Calibration Tokens, Model=DepthAnything, Train Dataset=Mix 200K, Zero-shot=true2025.082.04381
DepthAnyCameraExperiment=Comparisons, Model=DepthAnyCamera, Train Dataset=Outdoor 130K, Zero-shot=true2025.082.06785.2
UniDepthExperiment=Baseline, Model=UniDepth, Train Dataset=Mix 16M, Zero-shot=true2025.082.08566.3
DepthAnythingExperiment=Baseline, Model=DepthAnything, Train Dataset=Mix 63.5M, Zero-shot=true2025.082.21483.9
MiDaS + Calibration TokensExperiment=+ Calibration Tokens, Model=MiDaS, Train Dataset=Mix 200K, Zero-shot=true2025.082.34865.8
FoVA-DepthExperiment=Comparisons, Model=FoVA-Depth, Train Dataset=Outdoor 80K, Zero-shot=true2025.083.09663.2
MiDaSExperiment=Baseline, Model=MiDaS, Train Dataset=Mix 1.4M, Zero-shot=true2025.083.31258.6
DepthAnyCameraExperiment=Comparisons, Model=DepthAnyCamera, Train Dataset=Mix 200K, Zero-shot=true2025.085.67534.8