An Introduction to Image Synthesis with Generative Adversarial Nets

TL;DR

This paper provides an overview of Generative Adversarial Nets (GANs), focusing on their application to image synthesis, including methods, models, evaluation metrics, and future research directions.

Contribution

It offers a comprehensive taxonomy and review of GAN-based image synthesis methods, highlighting recent advances and challenges.

Findings

GANs have achieved impressive performance in image synthesis.

Various models for text-to-image and image-to-image translation are reviewed.

Discussion on evaluation metrics and future research directions.

Abstract

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.