Monocular Depth Estimation on KITTI Eigen (test)
0.029AbsRelSPIDepth
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| SPIDepthtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.029 | 0.069 | 1.394 | 0.048 | 0.99 | 0.999 | 1 | — | — | — | |
| LightedDepthtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.041 | 0.107 | 1.748 | 0.059 | 0.989 | 0.998 | 0.999 | — | — | — | |
| SQLdepthtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.043 | 0.105 | 1.698 | 0.064 | 0.983 | 0.998 | 0.999 | — | — | — | |
| DepthAnythingSupervised=true, Protocol=Fine-tuning2026.04 | 0.046 | — | 1.896 | 0.069 | 0.982 | 0.9998 | 0.9999 | — | — | — | |
| GEDepthtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.048 | 0.142 | 2.044 | 0.076 | 0.976 | 0.997 | 0.999 | — | — | — | |
| EVPtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.048 | 0.136 | 2.015 | 0.073 | 0.98 | 0.998 | 1 | — | — | — | |
| MGBackbone=Swin-L2023.03 | 0.05 | — | 0.202 | 0.075 | 0.976 | — | — | — | — | 6.757 | |
| IEBinsTraining Domain=Domain-specific2023.12 | 0.05 | 0.142 | 2.011 | 0.075 | 0.978 | 0.998 | 0.999 | — | — | — | |
| MIMTraining Domain=Domain-specific2023.12 | 0.05 | 0.139 | 1.966 | 0.075 | 0.977 | 0.998 | 1 | — | — | — | |
| iDisctraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.05 | 0.148 | 2.072 | 0.076 | 0.975 | 0.997 | 0.999 | — | — | — | |
| NDDepthtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.05 | 0.141 | 2.025 | 0.075 | 0.978 | 0.998 | 0.999 | — | — | — | |
| SwinV2-L 1K-MIMtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.05 | 0.139 | 1.966 | 0.075 | 0.977 | 0.998 | 1 | — | — | — | |
| PixelFormerTraining Domain=Domain-specific2023.12 | 0.051 | 0.149 | 2.081 | 0.077 | 0.976 | 0.997 | 0.999 | — | — | — | |
| NeWCRFsBackbone=Swin-L2023.03 | 0.052 | — | 0.213 | 0.079 | 0.974 | — | — | — | — | 6.986 | |
| NeWCRFsTraining Domain=Domain-specific2023.12 | 0.052 | 0.155 | 2.129 | 0.079 | 0.974 | 0.997 | 0.999 | — | — | — | |
| BinsFormerTraining Domain=Domain-specific2023.12 | 0.052 | 0.151 | 2.098 | 0.079 | 0.974 | 0.997 | 0.999 | — | — | — | |
| NeWCRFstraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.052 | 0.155 | 2.129 | 0.079 | 0.974 | 0.997 | 0.999 | — | — | — | |
| DMD-MIXTraining Domain=Joint indoor-outdoor2023.12 | 0.053 | 0.203 | 2.411 | 0.084 | 0.967 | 0.995 | 0.999 | — | — | — | |
| DDVMTraining Domain=Domain-specific2023.12 | 0.055 | 0.292 | 2.613 | 0.089 | 0.965 | 0.994 | 0.998 | — | — | — | |
| DMD-NKTraining Domain=Joint indoor-outdoor2023.12 | 0.055 | 0.219 | 2.527 | 0.087 | 0.964 | 0.994 | 0.999 | — | — | — | |
| ZoeD-M12-NKTraining Domain=Joint indoor-outdoor2023.12 | 0.057 | 0.204 | 2.362 | 0.087 | 0.966 | 0.993 | 0.996 | — | — | — | |
| ZoeDepthtraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.057 | 0.194 | 2.29 | 0.091 | 0.967 | 0.995 | 0.999 | — | — | — | |
| AdaBinsBackbone=EffNet-B5+ViT-mini2023.03 | 0.058 | — | 0.236 | 0.089 | 0.964 | — | — | — | — | 8.022 | |
| ASTransBackbone=ViT-B2023.03 | 0.058 | — | 0.269 | 0.089 | 0.963 | — | — | — | — | 7.897 | |
| AdaBinsTraining Domain=Domain-specific2023.12 | 0.058 | 0.19 | 2.36 | 0.088 | 0.964 | 0.995 | 0.999 | — | — | — | |
| AdaBinstraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.058 | 0.19 | 2.36 | 0.088 | 0.964 | 0.995 | 0.999 | — | — | — | |
| AdabinsSupervised=true, Protocol=Fine-tuning2026.04 | 0.058 | — | 2.36 | 0.088 | 0.964 | 0.995 | 0.999 | — | — | — | |
| BTSTraining Domain=Domain-specific2023.12 | 0.059 | 0.245 | 2.756 | 0.096 | 0.956 | 0.993 | 0.998 | — | — | — | |
| BTSBackbone=DenseNet-1612023.03 | 0.06 | — | 0.28 | 0.096 | 0.955 | — | — | — | — | 8.933 | |
| BTStraining=self-supervised pre-trained and metric fine-tuned2024.04 | 0.061 | 0.261 | 2.834 | 0.099 | 0.954 | 0.992 | 0.998 | — | — | — | |
| DPT-HybridBackbone=ViT-B2023.03 | 0.062 | — | 0.257 | 0.092 | 0.959 | — | — | — | — | 8.282 | |
| DPTTraining Domain=Domain-specific2023.12 | 0.062 | — | 2.573 | 0.092 | 0.959 | 0.995 | 0.999 | — | — | — | |
| DPTSupervised=true, Protocol=Fine-tuning2026.04 | 0.062 | — | 2.573 | 0.092 | 0.959 | 0.9995 | 0.999 | — | — | — | |
| TransDepthBackbone=ViT-B2023.03 | 0.064 | — | 0.275 | 0.098 | 0.956 | — | — | — | — | 8.93 | |
| SS3DSupervised=false, Protocol=Fine-tuning2026.04 | 0.064 | 0.53 | 3.212 | 0.138 | 0.946 | 0.977 | 0.986 | — | — | — | |
| DORNBackbone=ResNet-1012023.03 | 0.072 | — | 0.273 | 0.12 | 0.932 | — | — | — | — | — | |
| VNLBackbone=ResNeXt-1012023.03 | 0.072 | — | 0.326 | 0.117 | 0.938 | — | — | — | — | — | |
| Hariat et al.Supervised=false, Protocol=Fine-tuning2026.04 | 0.082 | 0.604 | 4.108 | 0.162 | 0.928 | 0.968 | 0.985 | — | — | — | |
| GeoDepthEvaluation Protocol=Scale-ambiguous2026.01 | 0.094 | 0.641 | 4.175 | 0.167 | 0.906 | 0.97 | 0.986 | — | — | — | |
| EDS-DepthEvaluation Protocol=Scale-ambiguous2026.01 | 0.095 | 0.619 | 4.184 | 0.17 | 0.905 | 0.969 | 0.985 | — | — | — | |
| RA-DepthSupervised=false, Protocol=Fine-tuning2026.04 | 0.096 | 0.613 | 4.216 | 0.171 | 0.903 | 0.968 | 0.985 | — | — | — | |
| MonoViTEvaluation Protocol=Scale-ambiguous2026.01 | 0.099 | 0.708 | 4.372 | 0.175 | 0.9 | 0.967 | 0.984 | — | — | — | |
| MonoViTSupervised=false, Protocol=Fine-tuning2026.04 | 0.099 | 0.708 | 4.372 | 0.175 | 0.9 | 0.967 | 0.984 | — | — | — | |
| DIFFNetSupervised=false, Protocol=Fine-tuning2026.04 | 0.102 | 0.764 | 4.483 | 0.18 | 0.896 | 0.965 | 0.983 | — | — | — | |
| HR-DepthSupervised=false, Protocol=Fine-tuning2026.04 | 0.109 | 0.792 | 4.632 | 0.185 | 0.884 | 0.962 | 0.983 | — | — | — | |
| Monodepth2Supervised=false, Protocol=Fine-tuning2026.04 | 0.11 | 0.831 | 4.642 | 0.187 | 0.883 | 0.962 | 0.982 | — | — | — | |
| Dyna-DMTraining Data=CityScape Only, maximum dynamic objects=202022.06 | 0.163 | 1.259 | 5.939 | 0.244 | 0.768 | 0.926 | 0.97 | — | — | — | |
| Insta-DMTraining Data=CityScape Only, maximum dynamic objects=132022.06 | 0.178 | 1.312 | 6.016 | 0.257 | 0.728 | 0.916 | 0.966 | — | — | — | |
| MarigoldReal training samples=None, Synthetic training samples=74K, Zero-shot=true, Ensemble=true2023.12 | 9.9 | — | — | — | 0.916 | — | — | — | — | — | |
| DPTReal training samples=1.2M, Synthetic training samples=188K, Zero-shot=true2023.12 | 10 | — | — | — | 0.901 | — | — | — | — | — | |
| MarigoldReal training samples=None, Synthetic training samples=74K, Zero-shot=true, Ensemble=false2023.12 | 10.5 | — | — | — | 0.904 | — | — | — | — | — | |
| HDNReal training samples=300K, Synthetic training samples=None, Zero-shot=true2023.12 | 11.5 | — | — | — | 0.867 | — | — | — | — | — | |
| LeReSReal training samples=300K, Synthetic training samples=54K, Zero-shot=true2023.12 | 14.9 | — | — | — | 0.784 | — | — | — | — | — | |
| OmnidataReal training samples=11.9M, Synthetic training samples=310K, Zero-shot=true2023.12 | 14.9 | — | — | — | 0.835 | — | — | — | — | — | |
| DiverseDepthReal training samples=320K, Synthetic training samples=None, Zero-shot=true2023.12 | 19 | — | — | — | 0.704 | — | — | — | — | — | |
| MiDaSReal training samples=2M, Synthetic training samples=None, Zero-shot=true2023.12 | 23.6 | — | — | — | 0.63 | — | — | — | — | — |