One-shot Face Reenactment Using Appearance Adaptive Normalization

TL;DR

This paper introduces a new GAN-based method for one-shot face reenactment that preserves identity while animating a face to new poses and expressions using appearance adaptive normalization.

Contribution

It presents a novel appearance adaptive normalization mechanism and a local facial component reenactment network for improved face animation from a single image.

Findings

Outperforms prior one-shot face reenactment methods in experiments.

Effectively preserves identity and captures expressions.

Enables detailed local facial component control.

Abstract

The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance. The core of our network is a novel mechanism called appearance adaptive normalization, which can effectively integrate the appearance information from the input image into our face generator by modulating the feature maps of the generator using the learned adaptive parameters. Furthermore, we specially design a local net to reenact the local facial components (i.e., eyes, nose and mouth) first, which is a much easier task for the network to learn and can in turn provide explicit anchors to guide our face generator to learn the global appearance and pose-and-expression. Extensive quantitative and qualitative experiments demonstrate the significant efficacy of our model compared with prior one-shot methods.