Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments. Learning pose-invariant features is one solution, but needs expensively labeled large scale data and carefully designed feature learning algorithms. In this work, we focus on frontalizing faces in the wild under various head poses, including extreme profile views. We propose a novel deep 3D Morphable Model (3DMM) conditioned Face Frontalization Generative Adversarial Network (GAN), termed as FF-GAN, to generate neutral head pose face images. Our framework differs from both traditional GANs and 3DMM based modeling. Incorporating 3DMM into the GAN structure provides shape and appearance priors for fast convergence with less training data, while also supporting end-to-end training. FF-GAN employs not only the discriminator and generator loss but also a new masked symmetry loss to retain visual quality under occlusions, besides an identity loss to recover high frequency information. Experiments on face recognition, landmark localization and 3D reconstruction consistently show the advantage of our frontalization method on faces in the wild datasets.
Face Frontalization on Multi-PIE
Face Frontalization on AFLW2000
Face Frontalization on LFW
Face Frontalization on IJB-A
We will release the frontalized LFW and AFLW2000 soon.
 Tal Hassner, Shai Harel, Eran Paz, and Roee Enbar. Effective face frontalization in unconstrained images. In CVPR, 2015
 Xiangyu Zhu, Zhen Lei, Junjie Yan, Dong Yi, and Stan Z. Li. High-fidelity pose and expression normalization for face recognition in the wild. In CVPR, 2015.