Monocular Depth Estimation on KITTI 2015 (test)
0.105Abs RelOurs without uncert. (V1)
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Ours without uncert. (V1)Learned Camera Intrinsics=true, Uncertainty=false2021.10 | 0.105 | 0.768 | 4.539 | 0.182 | 0.89 | 0.964 | 0.983 | |
| Johnston et al.Learned Camera Intrinsics=false2021.10 | 0.106 | 0.861 | 4.699 | 0.185 | 0.889 | 0.962 | 0.982 | |
| Ours with uncert. (V2)Learned Camera Intrinsics=true, Uncertainty=true2021.10 | 0.106 | 0.75 | 4.482 | 0.182 | 0.891 | 0.964 | 0.983 | |
| HR-DepthLearned Camera Intrinsics=false2021.10 | 0.109 | 0.792 | 4.632 | 0.185 | 0.884 | 0.962 | 0.983 | |
| PackNet-SFMLearned Camera Intrinsics=false2021.10 | 0.111 | 0.785 | 4.601 | 0.189 | 0.878 | 0.96 | 0.982 | |
| Learn Stereo, Infer Mono (ResNet)Training Dataset=CS + K, Backbone=ResNet, Post-processing=true2019.05 | 0.113 | 0.898 | 5.048 | 0.208 | 0.853 | 0.948 | 0.976 | |
| Godard et al.Training Dataset=CS + K2019.05 | 0.114 | 0.898 | 4.935 | 0.206 | 0.861 | 0.949 | 0.976 | |
| MonoDepth2Learned Camera Intrinsics=false2021.10 | 0.115 | 0.903 | 4.863 | 0.193 | 0.877 | 0.959 | 0.981 | |
| OursDataset (Train / Test)=Cityscapes / KITTI2026.05 | 0.116 | 0.892 | 4.892 | 0.195 | — | — | — | |
| OmegaNetLearned Camera Intrinsics=true2021.10 | 0.12 | 0.792 | 4.75 | 0.191 | 0.856 | 0.958 | 0.984 | |
| Learn Stereo, Infer Mono (VGG)Training Dataset=CS + K, Backbone=VGG, Post-processing=true2019.05 | 0.121 | 0.9643 | 5.137 | 0.213 | 0.846 | 0.944 | 0.976 | |
| CoopNetDataset (Train / Test)=Cityscapes / KITTI2026.05 | 0.125 | 1.157 | 5.251 | 0.209 | — | — | — | |
| Gordon et al.Learned Camera Intrinsics=true2021.10 | 0.128 | 0.959 | 5.23 | 0.212 | 0.845 | 0.947 | 0.976 | |
| GLNetDataset (Train / Test)=Cityscapes / KITTI2026.05 | 0.129 | 1.044 | 5.361 | 0.212 | — | — | — | |
| GLNetLearned Camera Intrinsics=true, Refinement=false2021.10 | 0.135 | 1.07 | 5.23 | 0.21 | 0.841 | 0.948 | 0.98 | |
| Yin et al.Training Dataset=CS + K2019.05 | 0.153 | 1.328 | 5.737 | 0.232 | 0.802 | 0.934 | 0.972 | |
| Zhou et al.Training Dataset=CS + K2019.05 | 0.198 | 1.836 | 6.565 | 0.275 | 0.718 | 0.901 | 0.96 | |
| Liu et al.Training Dataset=K2019.05 | 0.202 | 1.614 | 6.523 | 0.275 | 0.678 | 0.895 | 0.965 | |
| Eigen et al. - FineTraining Dataset=K, Mode=Fine2019.05 | 0.203 | 1.548 | 6.307 | 0.282 | 0.702 | 0.89 | 0.958 | |
| SFMlearnerLearned Camera Intrinsics=false2021.10 | 0.208 | 1.768 | 6.958 | 0.283 | 0.678 | 0.885 | 0.957 | |
| Eigen et al. - CoarseTraining Dataset=K, Mode=Coarse2019.05 | 0.214 | 1.605 | 6.563 | 0.292 | 0.673 | 0.884 | 0.957 | |
| Train set meanTraining Dataset=K2019.05 | 0.361 | 4.826 | 8.102 | 0.377 | 0.638 | 0.804 | 0.894 |