Monocular Depth Estimation on Make3D (test)
0.198Abs RelLaina et al.
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Laina et al.Trained on Make3D=true2019.04 | 0.198 | 1.665 | 5.461 | — | — | — | |
| Laina et al.Supervision=Full2019.05 | 0.198 | 1.665 | 5.461 | 0.082 | — | — | |
| Laina et al.Trained on target dataset=true2020.06 | 0.198 | 1.665 | 5.461 | — | — | — | |
| Laina et al.Supervised=Yes2022.09 | 0.198 | 1.665 | 5.461 | — | — | — | |
| Laina et al.Supervised=Yes2022.09 | 0.198 | 1.665 | 5.461 | — | — | — | |
| Laina et al.Supervision=Depth2017.04 | 0.204 | 1.84 | 5.683 | 0.084 | — | — | |
| LainaSupervision=GT2021.10 | 0.204 | 1.84 | 5.683 | 0.084 | — | — | |
| LainaSupervision=true, Zero-shot generalization=true2020.06 | 0.204 | 1.84 | 5.683 | — | — | — | |
| LainaType=D2021.12 | 0.204 | 1.84 | 5.683 | — | 0.084 | — | |
| Flex-X-Largeevaluation_mode=Zero-Shot, training_dataset=KITTI2026.07 | 0.279 | — | — | — | — | 61.1 | |
| Flex-X-Largevariant=X-Large2026.07 | 0.279 | 2.799 | 6.599 | 0.144 | — | — | |
| SCIPaDEvaluation Mode=Zero-shot, Pre-trained on=KITTI, Crop ratio=2:1 center-cropped2024.07 | 0.284 | 2.712 | 6.593 | 0.147 | — | — | |
| MonoViTTraining Dataset=KITTI, Training Resolution=640 x 1922022.08 | 0.286 | 2.758 | 6.623 | 0.147 | — | — | |
| MonoViTEvaluation Mode=Zero-shot, Pre-trained on=KITTI, Crop ratio=2:1 center-cropped2024.07 | 0.286 | 2.758 | 6.623 | 0.147 | — | — | |
| DSI-MonoVitevaluation_mode=Zero-Shot, training_dataset=KITTI2026.07 | 0.288 | — | — | — | — | 59.5 | |
| DCPI-DepthTraining Dataset=KITTI [43], Resolution=640x1922024.05 | 0.291 | 2.944 | 6.817 | 0.15 | — | — | |
| Flex-Mediumvariant=Medium2026.07 | 0.292 | 2.864 | 6.686 | 0.152 | — | — | |
| GeoDepth2026.07 | 0.296 | 2.75 | 6.735 | 0.153 | — | — | |
| MonoDiffusionTraining Dataset=KITTI [43], Resolution=640x1922024.05 | 0.297 | 2.871 | 6.877 | 0.156 | — | — | |
| DIFFNetTraining Dataset=KITTI, Training Resolution=640 x 1922022.08 | 0.298 | 2.901 | 6.753 | 0.153 | — | — | |
| DIFFNetEvaluation Mode=Zero-shot, Pre-trained on=KITTI, Crop ratio=2:1 center-cropped2024.07 | 0.298 | 2.901 | 6.753 | 0.153 | — | — | |
| SPIDepthType=M, Evaluation Mode=Zero-shot (KITTI pretrained)2024.04 | 0.299 | 1.931 | 6.672 | — | 0.144 | — | |
| PuriLightParams=2.7M2026.02 | 0.299 | 2.922 | 6.973 | 0.157 | — | — | |
| ARNSupervision=false, Zero-shot generalization=true2020.06 | 0.305 | 2.869 | 7.32 | — | — | — | |
| Lite-MonoTrained on=KITTI, Resolution=640 x 192, Zero-shot=true2022.11 | 0.305 | 3.06 | 6.981 | 0.158 | — | — | |
| HR-DepthTraining Dataset=KITTI, Training Resolution=640 x 1922022.08 | 0.305 | 2.944 | 6.857 | 0.157 | — | — | |
| HR-DepthEvaluation Mode=Zero-shot, Pre-trained on=KITTI, Crop ratio=2:1 center-cropped2024.07 | 0.305 | 2.944 | 6.857 | 0.157 | — | — | |
| HR-DepthTraining Dataset=KITTI [43], Resolution=640x1922024.05 | 0.305 | 2.944 | 6.857 | 0.157 | — | — | |
| Lite-MonoTraining Dataset=KITTI [43], Resolution=640x1922024.05 | 0.305 | 3.06 | 6.981 | 0.158 | — | — | |
| Lite-MonoParams=3.1M2026.02 | 0.305 | 3.06 | 6.981 | 0.158 | — | — | |
| Lite-Monovariant=Base2026.07 | 0.305 | 3.06 | 6.981 | 0.158 | — | — | |
| SQLdepthType=M, Zero-shot=true, Pre-training=KITTI, Evaluation protocol=center crop 2x12023.09 | 0.306 | 2.402 | 6.856 | — | 0.151 | — | |
| SQLdepthType=M, Evaluation Mode=Zero-shot (KITTI pretrained)2024.04 | 0.306 | 2.402 | 6.856 | — | 0.151 | — | |
| X-DistillSupervision=M, utilize semantic information during training=true2021.10 | 0.308 | 3.122 | 7.015 | 0.158 | — | — | |
| Lite-Mono-8mvariant=8m2026.07 | 0.309 | 3.145 | 7.016 | 0.158 | — | — | |
| Lite-Mono-Smallvariant=Small2026.07 | 0.31 | 2.878 | 6.842 | 0.16 | — | — | |
| Proposed Methodtrained_on=KITTI, fine-tuning=none2019.08 | 0.312 | — | — | — | — | — | |
| CADepth-NetType=M2021.12 | 0.312 | 3.086 | 7.066 | — | 0.159 | — | |
| CADepthNetType=M, Zero-shot=true, Pre-training=KITTI, Evaluation protocol=center crop 2x12023.09 | 0.312 | 3.086 | 7.066 | — | 0.159 | — | |
| CADepthNetType=M, Evaluation Mode=Zero-shot (KITTI pretrained)2024.04 | 0.312 | 3.086 | 7.066 | — | 0.159 | — | |
| Flex-Smallvariant=Small2026.07 | 0.315 | 3.127 | 6.865 | 0.159 | — | — | |
| Lite-Mono-Tinyvariant=Tiny2026.07 | 0.318 | 3.217 | 7.234 | 0.164 | — | — | |
| CADepthTraining Dataset=KITTI, Training Resolution=640 x 1922022.08 | 0.319 | 3.564 | 7.152 | 0.158 | — | — | |
| CADepthEvaluation Mode=Zero-shot, Pre-trained on=KITTI, Crop ratio=2:1 center-cropped2024.07 | 0.319 | 3.564 | 7.152 | 0.158 | — | — | |
| CCzero-shot=true, training_data=Cityscapes and KITTI2018.05 | 0.32 | — | — | — | — | — | |
| CCtrained_on=KITTI, fine-tuning=none2019.08 | 0.32 | — | — | — | — | — | |
| Monodepth2Training Dataset=KITTI, Training Resolution=640 x 1922022.08 | 0.321 | 3.378 | 7.252 | 0.163 | — | — | |
| Monodepth2Evaluation Mode=Zero-shot, Pre-trained on=KITTI, Crop ratio=2:1 center-cropped2024.07 | 0.321 | 3.378 | 7.252 | 0.163 | — | — | |
| Monodepth2Training Dataset=KITTI [43], Resolution=640x1922024.05 | 0.321 | 3.378 | 7.252 | 0.163 | — | — | |
| Monodepth2Supervision=M, Backbone=ResNet-182021.10 | 0.322 | 3.589 | 7.417 | 0.163 | — | — | |
| Monodepth2Supervision=false, Zero-shot generalization=true2020.06 | 0.322 | 3.589 | 7.417 | — | — | — | |
| Monodepth2Type=M2021.12 | 0.322 | 3.589 | 7.417 | — | 0.163 | — | |
| Monodepth2Trained on=KITTI, Resolution=640 x 192, Zero-shot=true2022.11 | 0.322 | 3.589 | 7.417 | 0.163 | — | — | |
| Monodepth2Type=M, Zero-shot=true, Pre-training=KITTI, Evaluation protocol=center crop 2x12023.09 | 0.322 | 3.589 | 7.417 | — | 0.163 | — | |
| Monodepth2Type=M, Evaluation Mode=Zero-shot (KITTI pretrained)2024.04 | 0.322 | 3.589 | 7.417 | — | 0.163 | — | |
| Monodepth2Params=14.3M2026.02 | 0.322 | 3.589 | 7.417 | 0.163 | — | — | |
| Monodepth22026.07 | 0.322 | 3.589 | 7.417 | 0.163 | — | — | |
| DF-Netzero-shot=true2018.05 | 0.331 | — | — | — | — | — | |
| DF-Net et al.trained_on=KITTI, fine-tuning=none2019.08 | 0.331 | — | — | — | — | — | |
| R-MSFM6Trained on=KITTI, Resolution=640 x 192, Zero-shot=true2022.11 | 0.334 | 3.285 | 7.212 | 0.169 | — | — | |
| R-MSFM6Training Dataset=KITTI [43], Resolution=640x1922024.05 | 0.334 | 3.285 | 7.212 | 0.169 | — | — | |
| R-MSFM6Params=3.8M2026.02 | 0.334 | 3.285 | 7.212 | 0.169 | — | — | |
| EPC++ (stereo)Training Data=K2018.10 | 0.341 | 3.86 | 7.65 | 0.392 | — | — | |
| EPC++ (stereo depth only)Training Data=K2018.10 | 0.346 | 3.97 | 7.7 | 0.395 | — | — | |
| 3D-PLSupervised=No2022.09 | 0.352 | 3.539 | 7.967 | — | — | — | |
| 3D-PLSupervised=No2022.09 | 0.352 | 3.539 | 7.967 | — | — | — | |
| Godardzero-shot=true2018.05 | 0.361 | — | — | — | — | — | |
| Godard et al. [22]Training Data=K2018.10 | 0.361 | 4.17 | 7.82 | 0.175 | — | — | |
| EPC++ (mono)Training Data=K2018.10 | 0.368 | 4.22 | 7.87 | 0.409 | — | — | |
| EPC++ (mono depth only)Training Data=K2018.10 | 0.374 | 4.6 | 8.17 | 0.414 | — | — | |
| SharinGANTrained on target dataset=false2020.06 | 0.377 | 4.9 | 8.388 | — | — | — | |
| SharinGANSupervised=No2022.09 | 0.377 | 4.9 | 8.388 | — | — | — | |
| SharinGANSupervised=No2022.09 | 0.377 | 4.9 | 8.388 | — | — | — | |
| SfMLearnerSupervision=None2017.04 | 0.383 | 5.321 | 10.47 | 0.478 | — | — | |
| Zhouzero-shot=true2018.05 | 0.383 | — | — | — | — | — | |
| SfMLearner [10]Training Data=CS+K2018.10 | 0.383 | 5.32 | 10.47 | 0.478 | — | — | |
| Zhou et al.trained_on=KITTI, fine-tuning=none2019.08 | 0.383 | — | — | — | — | — | |
| Zhou et al.Supervision=M2021.10 | 0.383 | 5.321 | 10.47 | 0.478 | — | — | |
| SfMLearnerSupervision=false, Zero-shot generalization=true2020.06 | 0.383 | 5.321 | 10.47 | — | — | — | |
| ZhouType=M2021.12 | 0.383 | 5.321 | 10.47 | — | 0.478 | — | |
| ZhouType=M, Zero-shot=true, Pre-training=KITTI, Evaluation protocol=center crop 2x12023.09 | 0.383 | 5.321 | 10.47 | — | 0.478 | — | |
| ZhouType=M, Evaluation Mode=Zero-shot (KITTI pretrained)2024.04 | 0.383 | 5.321 | 10.47 | — | 0.478 | — | |
| DDVO [82]Training Data=K2018.10 | 0.387 | 4.72 | 8.09 | 0.204 | — | — | |
| DDVOSupervision=M2021.10 | 0.387 | 4.72 | 8.09 | 0.204 | — | — | |
| DDVOSupervision=false, Zero-shot generalization=true2020.06 | 0.387 | 4.72 | 8.09 | — | — | — | |
| DDVOType=M2021.12 | 0.387 | 4.72 | 8.09 | — | 0.204 | — | |
| DDVOTrained on=KITTI, Resolution=640 x 192, Zero-shot=true2022.11 | 0.387 | 4.72 | 8.09 | 0.204 | — | — | |
| DDVOType=M, Zero-shot=true, Pre-training=KITTI, Evaluation protocol=center crop 2x12023.09 | 0.387 | 4.72 | 8.09 | — | 0.204 | — | |
| DDVOType=M, Evaluation Mode=Zero-shot (KITTI pretrained)2024.04 | 0.387 | 4.72 | 8.09 | — | 0.204 | — | |
| DDVOParams=28.1M2026.02 | 0.387 | 4.72 | 8.09 | 0.204 | — | — | |
| DESCSupervised=No2022.09 | 0.393 | 4.604 | 8.126 | — | — | — | |
| DESCSupervised=No2022.09 | 0.393 | 4.604 | 8.126 | — | — | — | |
| Karsch et al.Trained on Make3D=true2019.04 | 0.398 | 4.723 | 7.801 | — | — | — | |
| Karsh et al.Trained on target dataset=true2020.06 | 0.398 | 4.723 | 7.801 | — | — | — | |
| Karsch et al.Supervised=Yes2022.09 | 0.398 | 4.723 | 7.801 | — | — | — | |
| Karsch et al.Supervised=Yes2022.09 | 0.398 | 4.723 | 7.801 | — | — | — | |
| GASDATrained on Make3D=false2019.04 | 0.403 | 6.709 | 10.424 | — | — | — | |
| GASDATrained on target dataset=false2020.06 | 0.403 | 6.709 | 10.424 | — | — | — | |
| GASDASupervised=No2022.09 | 0.403 | 6.709 | 10.424 | — | — | — | |
| GASDASupervised=No2022.09 | 0.403 | 6.709 | 10.424 | — | — | — |