List your company
ResearchFormerly WizWand

Affine-invariant Depth Estimation on DIODE Full

0.136AbsRelOurs CSTM_label (ViT-giant)
-1.362568.7527218.86828.98328Mar 22, 2024Jul 20, 2024Nov 18, 2024Mar 19, 2025Jul 18, 2025Nov 16, 2025Mar 17, 2026
Updated 7mo ago

Evaluation results

MethodLinks
Ours CSTM_label (ViT-giant)Backbone=ViT-giant, #Params=1011M, Pretrain=142M, #Data Train=16M, Zero-shot transfer=true2024.030.1360.895
Ours CSTM_label (ViT-Large)Backbone=ViT-Large, #Params=306M, Pretrain=142M, #Data Train=16M, Zero-shot transfer=true2024.030.1410.882
DPT-largeBackbone=ViT-Large, Pretrain=1.3M, #Data Train=188K, Zero-shot transfer=true2024.030.1820.78
Ours CSTM_image (ConvNeXt-Large)Backbone=ConvNeXt-Large, #Params=198M, Pretrain=14.2M, #Data Train=8M, Zero-shot transfer=true2024.030.2110.825
Ours CSTM_label (ConvNeXt-Large)Backbone=ConvNeXt-Large, #Params=198M, Pretrain=14.2M, #Data Train=8M, Zero-shot transfer=true2024.030.2240.805
HDNBackbone=ViT-Large, #Params=306M, Pretrain=1.3M, #Data Train=300K, Zero-shot transfer=true2024.030.2460.882
Ours CSTM_label (ViT-Small)Backbone=ViT-Small, #Params=22M, Pretrain=142M, #Data Train=16M, Zero-shot transfer=true2024.030.2470.789
LeresBackbone=ResNeXt101, Pretrain=1.3M, #Data Train=354K, Zero-shot transfer=true2024.030.2710.766
DepthAnythingBackbone=ViT-Large, #Params=142M, Pretrain=142M, #Data Train=63.5M, Zero-shot transfer=true2024.030.2770.759
MarigoldBackbone=Latent diffusion V2, #Params=899M, Pretrain=5B, #Data Train=74K, Zero-shot transfer=true2024.030.3080.773
MiDaSBackbone=ResNeXt101, #Params=88M, Pretrain=1.3M, #Data Train=2M, Zero-shot transfer=true2024.030.3320.715
OmnidataBackbone=ViT-Base, Pretrain=1.3M, #Data Train=12.2M, Zero-shot transfer=true2024.030.3390.742
DiverseDepthBackbone=ResNeXt50, #Params=25M, Pretrain=1.3M, #Data Train=320K, Zero-shot transfer=true2024.030.3760.631
DPTTraining Data=1.4M, Zero-shot=true2026.0318.20.758
Lotus-D*Training Data=59K, Zero-shot=true2026.0322.80.738
GenPercept*Training Data=90K, Zero-shot=true2026.0322.80.74
Lotus-G*Training Data=59K, Zero-shot=true2026.0322.90.729
IrisTraining Data=59K + 100K, Zero-shot=true2026.0324.30.743
HDNTraining Data=300K, Zero-shot=true2026.0324.60.78
DepthAnythingTraining Data=62.6M, Zero-shot=true2026.03260.759
DepthAnything V2Training Data=62.6M, Zero-shot=true2026.0326.50.734
LeResTraining Data=354K, Zero-shot=true2026.0327.10.766
Diffusion-E2E-FT*Training Data=74K, Zero-shot=true2026.0330.30.776
Marigold(LCM)*Training Data=74K, Zero-shot=true2026.0330.70.775
Marigold*Training Data=74K, Zero-shot=true2026.0330.80.773
MiDaSTraining Data=2M, Zero-shot=true2026.0333.20.715
GeoWizard*Training Data=280K, Zero-shot=true2026.0333.50.723
OmnidataTraining Data=12.2M, Zero-shot=true2026.0333.90.742
DiverseDepthTraining Data=320K, Zero-shot=true2026.0337.60.631