3D Face Reconstruction On Aflw2000 3D
Metriken
Mean NME
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Mean NME | Paper Title | Repository |
|---|---|---|---|
| 3DDFA | 5.3695% | Face Alignment Across Large Poses: A 3D Solution | - |
| VGG-F | 3.42% | Pre-training strategies and datasets for facial representation learning | |
| B-spline FFD | 3.51% | Learning Free-Form Deformation for 3D Face Reconstruction from In-The-Wild Images | - |
| DSFNet-is | - | DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment | |
| SADRNet | 3.25% | SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction | |
| 3DDFA-V2 | 3.56% | Towards Fast, Accurate and Stable 3D Dense Face Alignment | |
| PRN | 3.9625% | Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network | |
| DeFA | 5.6454% | Dense Face Alignment |
0 of 8 row(s) selected.