ApprGAN: appearance‐based GAN for facial expression synthesis. Issue 14 (1st December 2019)

• Record Type: Journal Article
• Authors: Peng, Yao; Yin, Hujun
• Is Part Of: IET image processing. Volume 13:Issue 14(2019)
• Page Start: 2706
• Page End: 2715
• Publication Date: 2019-12-01
• Subjects: computer vision -- face recognition -- image texture -- computer animation -- neural nets -- learning (artificial intelligence); ApprGAN -- appearance‐based GAN -- generative adversarial nets -- image‐to‐image translation -- appearance‐based facial expression synthesis framework -- input face image -- texture generators -- synthetic shape deformation -- expression detail generation -- cross‐database synthesis -- photorealistic identity‐preserving expressions -- photorealistic image generation -- cycle‐consistency -- face synthesis synthesis -- computer vision -- animation -- identity mapping -- adversarial learning -- image texture -- quantitative verification; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6576
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Facial expression synthesis has drawn increasing attention in computer vision, graphics and animation. Recently, generative adversarial nets (GANs) have become a new perspective for face synthesis and have had remarkable success in generating photorealistic images and image‐to‐image translation. In this study, the authors present an appearance‐based facial expression synthesis framework, ApprGAN, by combining shape and texture and introducing cycle consistency and identity mapping into the adversarial learning. Specifically, given an input face image, a pair of shape and texture generators are trained for synthetic shape deformation and expression detail generation, respectively. Extensive experiments on expression synthesis and cross‐database synthesis were conducted, together with comparisons with the existing methods. Results of expression synthesis and quantitative verification on various databases show the effectiveness of ApprGAN in synthesising photorealistic and identity‐preserving expressions and its marked improvement over the existing methods.