FACEGAN: Facial Attribute Controllable rEenactment GAN

TL;DR

FACEGAN introduces a novel facial attribute controllable GAN that uses Action Units to transfer facial motion, effectively preventing identity leakage and allowing interpretable control, resulting in improved reenactment quality.

Contribution

The paper presents FACEGAN, a new GAN model that employs Action Units for facial motion transfer, enhancing reenactment accuracy and interpretability over existing landmark-based methods.

Findings

Outperforms state-of-the-art in single source reenactment

Prevents identity leakage with AU-based motion transfer

Separately processes background and face regions for better quality

Abstract

The face reenactment is a popular facial animation method where the person's identity is taken from the source image and the facial motion from the driving image. Recent works have demonstrated high quality results by combining the facial landmark based motion representations with the generative adversarial networks. These models perform best if the source and driving images depict the same person or if the facial structures are otherwise very similar. However, if the identity differs, the driving facial structures leak to the output distorting the reenactment result. We propose a novel Facial Attribute Controllable rEenactment GAN (FACEGAN), which transfers the facial motion from the driving face via the Action Unit (AU) representation. Unlike facial landmarks, the AUs are independent of the facial structure preventing the identity leak. Moreover, AUs provide a human interpretable way to control the reenactment. FACEGAN processes background and face regions separately for optimized output quality. The extensive quantitative and qualitative comparisons show a clear improvement over the state-of-the-art in a single source reenactment task. The results are best illustrated in the reenactment video provided in the supplementary material. The source code will be made available upon publication of the paper.