Towards Large-Pose Face Frontalization in the Wild

TL;DR

This paper introduces FF-GAN, a novel deep learning framework that combines 3D Morphable Models with GANs to effectively frontalize faces in unconstrained environments, including extreme poses, improving recognition and reconstruction tasks.

Contribution

The paper presents a new 3DMM-conditioned GAN architecture with a masked symmetry loss for robust face frontalization in the wild, reducing data requirements and enhancing visual quality.

Findings

Improved face recognition accuracy on wild datasets.

Enhanced landmark localization and 3D reconstruction results.

Effective frontalization of extreme pose faces.

Abstract

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. The 3DMM-conditioned 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.