GANimation: Anatomically-aware Facial Animation from a Single Image

TL;DR

This paper introduces a novel GAN-based method for facial expression synthesis that uses Action Units annotations to generate a wide range of anatomically feasible expressions from a single image, trained in an unsupervised manner.

Contribution

It presents a new GAN conditioning scheme based on Action Units, enabling continuous control of facial expressions and a fully unsupervised training strategy.

Findings

Outperforms existing methods in expression synthesis quality.

Capable of generating diverse, anatomically plausible expressions.

Robust to background and lighting variations.

Abstract

Recent advances in Generative Adversarial Networks (GANs) have shown impressive results for task of facial expression synthesis. The most successful architecture is StarGAN, that conditions GANs generation process with images of a specific domain, namely a set of images of persons sharing the same expression. While effective, this approach can only generate a discrete number of expressions, determined by the content of the dataset. To address this limitation, in this paper, we introduce a novel GAN conditioning scheme based on Action Units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression. Our approach allows controlling the magnitude of activation of each AU and combine several of them. Additionally, we propose a fully unsupervised strategy to train the model, that only requires images annotated with their activated AUs, and exploit attention mechanisms that make our network robust to changing backgrounds and lighting conditions. Extensive evaluation show that our approach goes beyond competing conditional generators both in the capability to synthesize a much wider range of expressions ruled by anatomically feasible muscle movements, as in the capacity of dealing with images in the wild.