Monocular Depth Estimation On Ibims 1
Métriques
RMSE
absolute relative error
δ1.25
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | RMSE | absolute relative error | δ1.25 | Paper Title | Repository |
|---|---|---|---|---|---|
| ScaleDepth-NK | 0.59 | 0.164 | 0.778 | ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation | - |
| Miangoleh et al. (SGR) | 0.1598 | - | 0.6390 | Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging | - |
| Metric3D-v2(L, ZS) | - | - | 0.969 | Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation | - |
| Miangoleh et al. (MiDaS) | 0.1965 | - | 0.7460 | Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging | - |
0 of 4 row(s) selected.