Monocular Depth Estimation On Eth3D
Metrics
Delta u003c 1.25
absolute relative error
Results
Performance results of various models on this benchmark
| Paper Title | |||
|---|---|---|---|
| Distill Any Depth | 0.981 | 0.054 | Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator |
| DepthMaster | 0.974 | 0.053 | DepthMaster: Taming Diffusion Models for Monocular Depth Estimation |
| PrimeDepth | 0.967 | 0.068 | PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage |
| Depth Anything | 0.882 | 0.0127 | Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data |
| MiDaS 3.1 | 0.867 | 0.0139 | MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation |
| Marigold | 0.0960 | 0.065 | Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation |
| DPT | 0.0946 | 0.078 | Vision Transformers for Dense Prediction |
| HDN | 0.0833 | 0.0121 | Hierarchical Normalization for Robust Monocular Depth Estimation |
| LeReS | 0.0777 | 0.0171 | Learning to Recover 3D Scene Shape from a Single Image |
| MiDaS | 0.0752 | 0.0184 | Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer |
0 of 10 row(s) selected.