Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Zeyu Ruan, Changqing Zou, Longhai Wu, Gangshan Wu, Limin Wang• 2021

Related benchmarks

TaskDatasetResultRank
Head Pose EstimationAFLW 3D 2000 (test)
MAE (Yaw)3.93
44
3D Face ReconstructionREALY (frontal-view)
Overall Error1.913
34
Face AlignmentAFLW2000-3D (test)
NME (Full height)3.46
29
3D Face ReconstructionAFLW2000-3D
NME0.0325
26
Single-view 3D face reconstructionREALY-S side-view--
24
Head Pose EstimationAFLW2000-3D
Yaw MAE2.93
20
3D Dense Face AlignmentAFLW2000-3D
NME (%)4.02
10
3D Dense Face AlignmentAFLW2000-3D NOD occlusion (test)
NME6.7
10
Single-view 3D face reconstructionREALY-F frontal-view
NMSE1.913
7
Single-view 3D face reconstructionFaceScape wild
CD7.12
7
Showing 10 of 12 rows

Other info

Follow for update