A Survey on Adversarial Image Synthesis

TL;DR

This survey reviews the advancements in adversarial image synthesis using GANs, covering various models, evaluation metrics, and future research directions in the field.

Contribution

It provides a comprehensive taxonomy of methods, reviews key models for text-to-image and image-to-image translation, and discusses evaluation metrics and future challenges.

Findings

GANs have significantly advanced image synthesis capabilities.

Various models enable text-to-image and image-to-image translation.

Evaluation metrics are crucial for assessing synthesis quality.

Abstract

Generative Adversarial Networks (GANs) have been extremely successful in various application domains. Adversarial image synthesis has drawn increasing attention and made tremendous progress in recent years because of its wide range of applications in many computer vision and image processing problems. 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.