Surface Normals Estimation On Nyu Depth V2 1
Metrics
% u003c 11.25
% u003c 22.5
% u003c 30
Mean Angle Error
RMSE
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | % u003c 11.25 | % u003c 22.5 | % u003c 30 | Mean Angle Error | RMSE |
|---|---|---|---|---|---|
| idisc-internal-discretization-for-monocular | 63.8 | 79.8 | 85.6 | 14.6 | 22.8 |
| metric3d-v2-a-versatile-monocular-geometric-1 | 68.8 | 84.9 | 89.8 | 12.0 | 19.2 |
| estimating-and-exploiting-the-aleatoric | 62.2 | 79.3 | 85.2 | 14.9 | 23.5 |
| polymax-general-dense-prediction-with-mask | 65.66 | 82.28 | 87.83 | 13.09 | 20.4 |
| fine-tuning-image-conditional-diffusion | 61.4 | - | - | 16.2 | - |
| floors-are-flat-leveraging-semantics-for-real | 59.5 | 72.2 | 77.3 | 19.7 | 19.3 |