Recent Progress of Face Image Synthesis
It addresses the problem of generating realistic face images for applications like face recognition, but it is incremental as it is a review paper summarizing existing progress.
This paper provides a comprehensive review of face image synthesis methods, including traditional and deep learning approaches, highlighting Generative Adversarial Networks (GANs) for generating photo-realistic and identity-preserving results.
Face synthesis has been a fascinating yet challenging problem in computer vision and machine learning. Its main research effort is to design algorithms to generate photo-realistic face images via given semantic domain. It has been a crucial prepossessing step of main-stream face recognition approaches and an excellent test of AI ability to use complicated probability distributions. In this paper, we provide a comprehensive review of typical face synthesis works that involve traditional methods as well as advanced deep learning approaches. Particularly, Generative Adversarial Net (GAN) is highlighted to generate photo-realistic and identity preserving results. Furthermore, the public available databases and evaluation metrics are introduced in details. We end the review with discussing unsolved difficulties and promising directions for future research.