SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
About
Three-dimensional face dense alignment and reconstruction in the wild is a challenging problem as partial facial information is commonly missing in occluded and large pose face images. Large head pose variations also increase the solution space and make the modeling more difficult. Our key idea is to model occlusion and pose to decompose this challenging task into several relatively more manageable subtasks. To this end, we propose an end-to-end framework, termed as Self-aligned Dual face Regression Network (SADRNet), which predicts a pose-dependent face, a pose-independent face. They are combined by an occlusion-aware self-alignment to generate the final 3D face. Extensive experiments on two popular benchmarks, AFLW2000-3D and Florence, demonstrate that the proposed method achieves significant superior performance over existing state-of-the-art methods.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Head Pose Estimation | AFLW 3D 2000 (test) | MAE (Yaw)3.93 | 44 | |
| 3D Face Reconstruction | REALY (frontal-view) | Overall Error1.913 | 34 | |
| Face Alignment | AFLW2000-3D (test) | NME (Full height)3.46 | 29 | |
| 3D Face Reconstruction | AFLW2000-3D | NME0.0325 | 26 | |
| Single-view 3D face reconstruction | REALY-S side-view | -- | 24 | |
| Head Pose Estimation | AFLW2000-3D | Yaw MAE2.93 | 20 | |
| 3D Dense Face Alignment | AFLW2000-3D | NME (%)4.02 | 10 | |
| 3D Dense Face Alignment | AFLW2000-3D NOD occlusion (test) | NME6.7 | 10 | |
| Single-view 3D face reconstruction | REALY-F frontal-view | NMSE1.913 | 7 | |
| Single-view 3D face reconstruction | FaceScape wild | CD7.12 | 7 |