An Introduction to Image Synthesis with Generative Adversarial Nets
This is an incremental survey paper that organizes existing knowledge about GANs for image synthesis, primarily benefiting researchers in computer vision.
This paper provides a taxonomy and review of Generative Adversarial Nets (GANs) methods for image synthesis, covering text-to-image synthesis and image-to-image translation, along with evaluation metrics and future directions.
There has been a drastic growth of research in Generative Adversarial Nets (GANs) in the past few years. Proposed in 2014, GAN has been applied to various applications such as computer vision and natural language processing, and achieves impressive performance. Among the many applications of GAN, image synthesis is the most well-studied one, and research in this area has already demonstrated the great potential of using GAN in image synthesis. In this paper, we provide a taxonomy of methods used in image synthesis, review different models for text-to-image synthesis and image-to-image translation, and discuss some evaluation metrics as well as possible future research directions in image synthesis with GAN.