Surface Normals Estimation On Nyu Depth V2 1
Métriques
% u003c 11.25
% u003c 22.5
% u003c 30
Mean Angle Error
RMSE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | % u003c 11.25 | % u003c 22.5 | % u003c 30 | Mean Angle Error | RMSE | Paper Title | Repository |
|---|---|---|---|---|---|---|---|
| iDisc | 63.8 | 79.8 | 85.6 | 14.6 | 22.8 | iDisc: Internal Discretization for Monocular Depth Estimation | |
| Metric3Dv2(L, FT) | 68.8 | 84.9 | 89.8 | 12.0 | 19.2 | Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation | |
| Bae et al. | 62.2 | 79.3 | 85.2 | 14.9 | 23.5 | Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation | |
| PolyMaX(ConvNeXt-L) | 65.66 | 82.28 | 87.83 | 13.09 | 20.4 | PolyMaX: General Dense Prediction with Mask Transformer | |
| Marigold + E2E FT(zero-shot) | 61.4 | - | - | 16.2 | - | Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think | |
| Floors are Flat | 59.5 | 72.2 | 77.3 | 19.7 | 19.3 | Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction |
0 of 6 row(s) selected.