Conditional Adversarial Synthesis of 3D Facial Action Units

TL;DR

This paper introduces a novel method for synthesizing 3D facial images conditioned on Action Unit labels, enhancing datasets for better facial expression analysis using deep learning.

Contribution

It combines 3D Morphable Models with adversarial networks to generate diverse facial expressions conditioned on AU labels, improving data augmentation techniques.

Findings

Effective synthesis of 3D facial expressions from AU labels

Improved AU intensity estimation accuracy

Enhanced dataset diversity for training deep models

Abstract

Employing deep learning-based approaches for fine-grained facial expression analysis, such as those involving the estimation of Action Unit (AU) intensities, is difficult due to the lack of a large-scale dataset of real faces with sufficiently diverse AU labels for training. In this paper, we consider how AU-level facial image synthesis can be used to substantially augment such a dataset. We propose an AU synthesis framework that combines the well-known 3D Morphable Model (3DMM), which intrinsically disentangles expression parameters from other face attributes, with models that adversarially generate 3DMM expression parameters conditioned on given target AU labels, in contrast to the more conventional approach of generating facial images directly. In this way, we are able to synthesize new combinations of expression parameters and facial images from desired AU labels. Extensive quantitative and qualitative results on the benchmark DISFA dataset demonstrate the effectiveness of our method on 3DMM facial expression parameter synthesis and data augmentation for deep learning-based AU intensity estimation.