# Expression Conditional GAN for Facial Expression-to-Expression Translation

## TL;DR

This paper introduces ECGAN, a versatile conditional GAN framework for facial expression translation that effectively controls expression generation and reduces background influence, validated across diverse real-world datasets.

## Contribution

The paper presents ECGAN, a novel conditional GAN with a face mask loss for improved expression translation and a combined generation-recognition framework for real-world facial analysis.

## Key findings

- Accurately generates facial expressions across diverse datasets.
- Robustly handles variations in race, illumination, occlusion, and pose.
- Outperforms existing methods in qualitative and quantitative evaluations.

## Abstract

In this paper, we focus on the facial expression translation task and propose a novel Expression Conditional GAN (ECGAN) which can learn the mapping from one image domain to another one based on an additional expression attribute. The proposed ECGAN is a generic framework and is applicable to different expression generation tasks where specific facial expression can be easily controlled by the conditional attribute label. Besides, we introduce a novel face mask loss to reduce the influence of background changing. Moreover, we propose an entire framework for facial expression generation and recognition in the wild, which consists of two modules, i.e., generation and recognition. Finally, we evaluate our framework on several public face datasets in which the subjects have different races, illumination, occlusion, pose, color, content and background conditions. Even though these datasets are very diverse, both the qualitative and quantitative results demonstrate that our approach is able to generate facial expressions accurately and robustly.