A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision

TL;DR

This paper provides a chronological survey of key theoretical advancements in GANs for computer vision, highlighting how challenges were addressed over time through landmark research works.

Contribution

It uniquely organizes GAN advancements in a timeline, emphasizing the sequential solving of challenges in GAN development.

Findings

Identifies major milestones in GAN theory and application.

Highlights the evolution of solutions to GAN training challenges.

Provides a chronological framework for GAN research progress.

Abstract

Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision. Accordingly, there have been many significant advancements in the theory and application of GAN models, which are notoriously hard to train, but produce good results if trained well. There have been many a surveys on GANs, organizing the vast GAN literature from various focus and perspectives. However, none of the surveys brings out the important chronological aspect: how the multiple challenges of employing GAN models were solved one-by-one over time, across multiple landmark research works. This survey intends to bridge that gap and present some of the landmark research works on the theory and application of GANs, in chronological order.