Expression Conditional GAN for Facial Expression-to-Expression Translation
This addresses facial expression generation and recognition in the wild, but it appears incremental as it builds on existing conditional GAN methods.
The paper tackles facial expression translation by proposing Expression Conditional GAN (ECGAN), a framework that learns to map between image domains using expression attributes, and introduces a face mask loss to reduce background interference. Results show it generates facial expressions accurately and robustly across diverse public datasets with varying races, illumination, occlusion, pose, color, content, and background conditions.
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.