SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
arXiv:2106.03021 · doi:10.1109/TIP.2021.3087397
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.
arXiv commentTo appear in IEEE Transactions on Image Processing. Code and model is available at https://github.com/MCG-NJU/SADRNet
References in corpus (9)
- How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
- Going Deeper in Facial Expression Recognition using Deep Neural Networks
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
- On Learning 3D Face Morphable Model from In-the-wild Images
- Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
- Multi-task head pose estimation in-the-wild
- Self-supervised Learning of Detailed 3D Face Reconstruction
- Fitting 3D Morphable Models using Local Features
- Two-stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge