SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

TL;DR

SADRNet is an end-to-end neural network that improves 3D face alignment and reconstruction in challenging conditions by modeling occlusion and pose variations, achieving superior results on benchmark datasets.

Contribution

The paper introduces SADRNet, a novel framework that decomposes 3D face reconstruction into pose-dependent and pose-independent components with self-alignment, enhancing robustness.

Findings

Outperforms state-of-the-art methods on AFLW2000-3D and Florence datasets.

Effectively handles occlusion and large pose variations.

Demonstrates significant accuracy improvements in 3D face reconstruction.

Abstract

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.