Geometry Guided Adversarial Facial Expression Synthesis
This work addresses the problem of generating realistic facial expressions for applications like face animation and recognition, but it is incremental as it builds on existing GAN methods with geometry guidance.
The paper tackles the challenge of facial expression synthesis by proposing a Geometry-Guided GAN (G2-GAN) that uses facial geometry as a condition to generate photo-realistic and identity-preserving expressions, with experimental results showing compelling perceptual outputs and advantages in expression-invariant face recognition.
Facial expression synthesis has drawn much attention in the field of computer graphics and pattern recognition. It has been widely used in face animation and recognition. However, it is still challenging due to the high-level semantic presence of large and non-linear face geometry variations. This paper proposes a Geometry-Guided Generative Adversarial Network (G2-GAN) for photo-realistic and identity-preserving facial expression synthesis. We employ facial geometry (fiducial points) as a controllable condition to guide facial texture synthesis with specific expression. A pair of generative adversarial subnetworks are jointly trained towards opposite tasks: expression removal and expression synthesis. The paired networks form a mapping cycle between neutral expression and arbitrary expressions, which also facilitate other applications such as face transfer and expression invariant face recognition. Experimental results show that our method can generate compelling perceptual results on various facial expression synthesis databases. An expression invariant face recognition experiment is also performed to further show the advantages of our proposed method.