A survey and taxonomy of adversarial neural networks for text‐to‐image synthesis

Abstract

AbstractText‐to‐image synthesis refers to computational methods which translate human written textual descriptions, in the form of keywords or sentences, into images with similar semantic meaning to the text. In earlier research, image synthesis relied mainly on word to image correlation analysis combined with supervised methods to find best alignment of the visual content matching to the text. Recent progress in deep learning (DL) has brought a new set of unsupervised DL methods, particularly deep generative models which are able to generate realistic visual images using suitably trained neural network models. The change of direction from the computer vision‐based approaches to artificial intelligence (AI)‐driven methods ignited the intense interest in industry, such as virtual reality, recreational & professional (eSports) gaming, and computer‐aided design, and so on, to automatically generate compelling images from text‐based natural language descriptions. In this paper, we review the most recent development in the text‐to‐image synthesis research domain. Our goal is to provide value by delivering a comparative review of the state‐of‐the‐art models in terms of their architecture and design. The survey first introduces image synthesis and its challenges, and then reviews key concepts such as generative adversarial networks (GANs) and deep convolutional encoder‐decoder neural networks (DCNNs). After that, we propose a taxonomy to summarize GAN‐based text‐to‐image synthesis into four major categories: semantic enhancement GANs, resolution enhancement GANs, diversity enhancement GANS, and motion enhancement GANs. We elaborate on the main objective of each group, and further review typical GAN architectures in each group. The taxonomy and the review outline the techniques and the evolution of different approaches, and eventually provide a roadmap to summarize the list of contemporaneous solutions that utilize GANs and DCNNs to generate enthralling results in categories such as human faces, birds, flowers, room interiors, object reconstruction from edge maps (games), and so on. The survey concludes with a comparison of the proposed solutions, challenges that remain unresolved, and future developments in the text‐to‐image synthesis domain.This article is categorized under: Algorithmic Development > Multimedia Technologies > Machine Learning