FExGAN-Meta: Facial Expression Generation with Meta Humans

TL;DR

This paper introduces FExGAN-Meta, a novel facial expression generation method tailored for Meta-Humans, leveraging a new dataset to improve robustness in generating and classifying diverse facial expressions.

Contribution

The paper presents a new dataset and a robust generative model specifically designed for Meta-Humans' facial expressions, addressing data quality and variability challenges.

Findings

FExGAN-Meta effectively generates diverse facial expressions.

The model accurately classifies both simple and complex expressions.

The dataset enhances model training and evaluation.

Abstract

The subtleness of human facial expressions and a large degree of variation in the level of intensity to which a human expresses them is what makes it challenging to robustly classify and generate images of facial expressions. Lack of good quality data can hinder the performance of a deep learning model. In this article, we have proposed a Facial Expression Generation method for Meta-Humans (FExGAN-Meta) that works robustly with the images of Meta-Humans. We have prepared a large dataset of facial expressions exhibited by ten Meta-Humans when placed in a studio environment and then we have evaluated FExGAN-Meta on the collected images. The results show that FExGAN-Meta robustly generates and classifies the images of Meta-Humans for the simple as well as the complex facial expressions.