FExGAN-Meta: Facial Expression Generation with Meta Humans

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.

Generating non-verbal responses in virtual agent with use of LSTM network

“…Another contribution is the FExGAN-Meta dataset and model [11], specifically designed for generating facial expressions in metahumans. The authors not only introduced a Facial Expression Generation model but also created a substantial dataset of metahuman facial images with corresponding expression labels.…”