F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks

TL;DR

This paper introduces F3A-GAN, a face animation method using a novel 3D facial flow representation to generate high-quality, continuous face images from a single source, outperforming previous approaches especially in complex scenarios.

Contribution

The paper proposes a new 3D geometric flow condition for face animation, enabling better control and continuity in generated images compared to existing 1D or 2D condition-based methods.

Findings

Outperforms state-of-the-art face animation methods.

Effectively handles large pose transformations.

Produces high-quality, continuous face images.

Abstract

Formulated as a conditional generation problem, face animation aims at synthesizing continuous face images from a single source image driven by a set of conditional face motion. Previous works mainly model the face motion as conditions with 1D or 2D representation (e.g., action units, emotion codes, landmark), which often leads to low-quality results in some complicated scenarios such as continuous generation and largepose transformation. To tackle this problem, the conditions are supposed to meet two requirements, i.e., motion information preserving and geometric continuity. To this end, we propose a novel representation based on a 3D geometric flow, termed facial flow, to represent the natural motion of the human face at any pose. Compared with other previous conditions, the proposed facial flow well controls the continuous changes to the face. After that, in order to utilize the facial flow for face editing, we build a synthesis framework generating continuous images with conditional facial flows. To fully take advantage of the motion information of facial flows, a hierarchical conditional framework is designed to combine the extracted multi-scale appearance features from images and motion features from flows in a hierarchical manner. The framework then decodes multiple fused features back to images progressively. Experimental results demonstrate the effectiveness of our method compared to other state-of-the-art methods.