Monocular Depth Estimation on 13 diverse datasets Zero-shot Aggregate (test)
6.76Rel^d (Scale-invariant)DepthMaster
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| DepthMaster2026.06 | 6.76 | 14.2 | 82.3 | 92.7 | 5.18 | 94.9 | 6.8 | 93.8 | 1.31 | |
| MoGe 22026.06 | 7.35 | 15.7 | 76.8 | 92.2 | 5.62 | 94.8 | 6.66 | 93.8 | 2.22 | |
| Metric3D V22026.06 | 7.92 | — | — | 91.8 | 7.66 | 92.9 | 9.51 | 89.4 | 5.67 | |
| UniK3D2026.06 | 8.26 | 15.5 | 82.5 | 91.1 | 6.5 | 93.8 | 7.38 | 93 | 2.75 | |
| UniDepth V22026.06 | 8.61 | 21.3 | 75.3 | 90.8 | 6.42 | 93.9 | 7.35 | 93 | 3.75 | |
| Depth Pro2026.06 | 9.81 | 27.6 | 54.4 | 89.1 | 7.65 | 92 | 8.42 | 91.7 | 5.5 | |
| UniDepth V12026.06 | 10.1 | 23.2 | 67.5 | 89.1 | 8.61 | 91 | 9.75 | 89.9 | 6.44 | |
| DA V2Training Protocol (Metric)=In-domain2026.06 | 10.7 | 29.9 | 56.6 | 87.6 | 8.48 | 90.8 | 8.82 | 91.6 | 7.13 | |
| MASt3R2026.06 | 11.2 | 49.7 | 30.3 | 86.5 | 9.38 | 89.1 | 11.6 | 87.8 | 8.25 | |
| DA V1Training Protocol (Metric)=In-domain2026.06 | 11.7 | 31.8 | 54.8 | 85.8 | 8.76 | 90.4 | 8.63 | 92.2 | 8 | |
| ZoeDepthTraining Protocol (Metric)=In-domain2026.06 | 12.7 | 39.3 | 49.9 | 83.9 | 10.1 | 88.5 | 11.1 | 88.3 | 10.25 |