NECVMay 17, 2016

Generative Adversarial Text to Image Synthesis

arXiv:1605.05396v23405 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of automatic image synthesis from text, which is useful for applications like content creation, but is incremental as it builds on existing GAN and RNN methods.

The paper tackled the problem of generating realistic images from text descriptions by developing a novel deep architecture and GAN formulation to bridge advances in text and image modeling, resulting in plausible images of birds and flowers from detailed text.

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.

Code Implementations39 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes