Facial Landmarks and Expression Label Guided Photorealistic Facial Expression Synthesis

• Published in: IEEE access Vol. 9; pp. 56292 - 56300
• Main Authors: Li, Dejian, Qi, Wenqian, Sun, Shouqian
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computer graphics; Faces; Facial expression synthesis; Gallium nitride; Generative adversarial networks; Generators; Shape; Synthesis; Target recognition; Three-dimensional displays; Two dimensional displays
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3072057

Facial expression manipulation plays an increasingly important role in the field of computer graphics and has been widely used in generating facial animations. However, it is still a very challenging task as it needs full understanding of the input face and very depending on the facial appearance. In this paper, we present an end-to-end generative adversarial network for facial expression synthesis. Given the facial landmarks and the expression label of a target image, our method automatically generates a corresponding expression facial image with the identity information and facial details well preserved. Both qualitative and quantitative experiments are conducted on the CK+ and Oulu-CASIA datasets. Experimental results show that our method has the compelling perceptual results even there exist large differences in facial shapes for unseen subjects.