Depth Estimation on NYU
0.039AbsRelMetric3D v2
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Metric3D v2Training Samples=16M, NFEs=-, Zero-shot=true2025.12 | 0.039 | 0.979 | 1.2 | |
| DepthAnythingTraining Samples=63.5K, NFEs=-, Zero-shot=true2025.12 | 0.043 | 0.98 | 2.2 | |
| DepthAnything v2Training Samples=62.6M, NFEs=-, Zero-shot=true2025.12 | 0.043 | 0.979 | 2.8 | |
| D3-PredictorTraining Samples=30K, NFEs=1 x 1, Zero-shot=true2025.12 | 0.052 | 0.97 | 2.1 | |
| Lotus-GTraining Samples=59K, NFEs=1 x 1, Zero-shot=true2025.12 | 0.054 | 0.966 | 3.3 | |
| E2E-FTTraining Samples=74K, NFEs=1 x 1, Zero-shot=true2025.12 | 0.054 | 0.965 | 3.1 | |
| MarigoldTraining Samples=74K, NFEs=10 x 50, Zero-shot=true2025.12 | 0.055 | 0.964 | 4.4 | |
| Unified-IOTraining Samples=48K, NFEs=-, Zero-shot=true2025.12 | 0.059 | 0.97 | 1.9 | |
| GeoWizardTraining Samples=280K, NFEs=10 x 50, Zero-shot=true2025.12 | 0.059 | 0.959 | 5.6 | |
| 4M-XLTraining Samples=759M, NFEs=-, Zero-shot=true2025.12 | 0.068 | 0.951 | 1.7 | |
| HDNTraining Samples=300K, NFEs=-, Zero-shot=true2025.12 | 0.069 | 0.948 | 3.9 | |
| DeceptionTraining Samples=500K, NFEs=1 x 28, Zero-shot=true2025.12 | 0.072 | 0.939 | 3.6 | |
| OmnidataTraining Samples=12.2M, NFEs=-, Zero-shot=true2025.12 | 0.074 | 0.945 | 5.1 | |
| DepthFMTraining Samples=63K, NFEs=10 x 4, Zero-shot=true2025.12 | 0.082 | 0.932 | 5.2 | |
| OneDiffusionTraining Samples=500K, NFEs=-, Zero-shot=true2025.12 | 0.087 | 0.924 | 2.4 | |
| GenperceptTraining Samples=90K, NFEs=1 x 1, Zero-shot=true2025.12 | 0.091 | 0.932 | 4 | |
| DPT-largeTraining Samples=1.4M, NFEs=-, Zero-shot=true2025.12 | 0.098 | 0.903 | 4.2 | |
| DMPTraining Samples=10K, NFEs=1 x 5, Zero-shot=true2025.12 | 0.109 | 0.891 | 7.7 | |
| MiDaSTraining Samples=2M, NFEs=-, Zero-shot=true2025.12 | 0.111 | 0.885 | 6.9 | |
| DiverseDepthTraining Samples=320K, NFEs=-, Zero-shot=true2025.12 | 0.117 | 0.875 | 7 |