Text to Image Synthesis Using Generative Adversarial Networks
This work addresses the problem of generating high-quality images from text descriptions for applications like photo editing and content creation, representing an incremental improvement over existing methods.
The paper tackles text-to-image synthesis by proposing Wasserstein GAN-CLS, a new model based on the Wasserstein distance for stable conditional image generation, and shows that combining it with a Conditional Progressive Growing GAN boosts the Inception Score by 7.07% on the Caltech birds dataset compared to models using only sentence-level visual semantics.
Generating images from natural language is one of the primary applications of recent conditional generative models. Besides testing our ability to model conditional, highly dimensional distributions, text to image synthesis has many exciting and practical applications such as photo editing or computer-aided content creation. Recent progress has been made using Generative Adversarial Networks (GANs). This material starts with a gentle introduction to these topics and discusses the existent state of the art models. Moreover, I propose Wasserstein GAN-CLS, a new model for conditional image generation based on the Wasserstein distance which offers guarantees of stability. Then, I show how the novel loss function of Wasserstein GAN-CLS can be used in a Conditional Progressive Growing GAN. In combination with the proposed loss, the model boosts by 7.07% the best Inception Score (on the Caltech birds dataset) of the models which use only the sentence-level visual semantics. The only model which performs better than the Conditional Wasserstein Progressive Growing GAN is the recently proposed AttnGAN which uses word-level visual semantics as well.