Generative Adversarial Text to Image Synthesis

TL;DR

This paper introduces a novel GAN-based architecture that translates detailed text descriptions into realistic images of objects like birds and flowers, advancing the field of text-to-image synthesis.

Contribution

It presents a new deep architecture and GAN formulation that effectively combines text and image modeling for realistic image generation from text.

Findings

Generated plausible images of birds and flowers from text descriptions

Demonstrated effectiveness of the model in translating text to images

Bridged advances in text feature representation and image synthesis

Abstract

Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to generate highly compelling images of specific categories, such as faces, album covers, and room interiors. In this work, we develop a novel deep architecture and GAN formulation to effectively bridge these advances in text and image model- ing, translating visual concepts from characters to pixels. We demonstrate the capability of our model to generate plausible images of birds and flowers from detailed text descriptions.