Text-To-Image with Generative Adversarial Networks

TL;DR

This paper compares five GAN-based text-to-image methods, analyzing their architectures and image resolutions, to identify the most effective approach for generating realistic images from textual descriptions.

Contribution

It provides a comparative analysis of different GAN architectures for text-to-image synthesis, highlighting their performance across various resolutions.

Findings

Best resolution achieved was 256x256

Model performance varied significantly across approaches

Identified the most effective GAN model for text-to-image generation

Abstract

Generating realistic images from human texts is one of the most challenging problems in the field of computer vision (CV). The meaning of descriptions given can be roughly reflected by existing text-to-image approaches. In this paper, our main purpose is to propose a brief comparison between five different methods base on the Generative Adversarial Networks (GAN) to make image from the text. In addition, each model architectures synthesis images with different resolution. Furthermore, the best and worst obtained resolutions is 64*64, 256*256 respectively. However, we checked and compared some metrics that introduce the accuracy of each model. Also, by doing this study, we found out the best model for this problem by comparing these different approaches essential metrics.