Surface Normals Estimation On Scannetv2
Metrics
% u003c 11.25
% u003c 22.5
% u003c 30
Mean Angle Error
Results
Performance results of various models on this benchmark
Model Name | % u003c 11.25 | % u003c 22.5 | % u003c 30 | Mean Angle Error | Paper Title | Repository |
|---|---|---|---|---|---|---|
| Metric3Dv2 (g2, In-domain) | 77.8 | 90.1 | 93.5 | 9.2 | Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation | |
| Bae et al. | 71.1 | 85.4 | 89.8 | 11.8 | Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation | |
| Floors are Flat | 50.9 | 65.2 | 70 | 28 | Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction |
0 of 3 row(s) selected.