Interleaving GANs with knowledge graphs to support design creativity for book covers

TL;DR

This paper introduces a novel method combining GANs with knowledge graphs to generate diverse and high-quality book cover images, aiding authors and editors in creative design choices.

Contribution

The paper presents a new approach that interleaves GANs with knowledge graphs to enhance book cover generation and provide multiple design options.

Findings

Outperforms previous book cover generation methods

Knowledge graphs improve diversity of generated options

Discriminator effectively selects the best images

Abstract

An attractive book cover is important for the success of a book. In this paper, we apply Generative Adversarial Networks (GANs) to the book covers domain, using different methods for training in order to obtain better generated images. We interleave GANs with knowledge graphs to alter the input title to obtain multiple possible options for any given title, which are then used as an augmented input to the generator. Finally, we use the discriminator obtained during the training phase to select the best images generated with new titles. Our method performed better at generating book covers than previous attempts, and the knowledge graph gives better options to the book author or editor compared to using GANs alone.