ComicGAN: Text-to-Comic Generative Adversarial Network
This work addresses the complex and difficult process of drawing and annotating comic illustrations for creators, though it is incremental as it builds on existing text-to-image GAN technology.
The authors tackled the problem of generating comic illustrations from text descriptions or dialogue, which had not been addressed by existing machine learning algorithms, and their ComicGAN pipeline produced synthetic comic panels that resembled original Dilbert panels, with improvements in Frechet Inception Distance, detail, and image quality over baselines.
Drawing and annotating comic illustrations is a complex and difficult process. No existing machine learning algorithms have been developed to create comic illustrations based on descriptions of illustrations, or the dialogue in comics. Moreover, it is not known if a generative adversarial network (GAN) can generate original comics that correspond to the dialogue and/or descriptions. GANs are successful in producing photo-realistic images, but this technology does not necessarily translate to generation of flawless comics. What is more, comic evaluation is a prominent challenge as common metrics such as Inception Score will not perform comparably, as they are designed to work on photos. In this paper: 1. We implement ComicGAN, a novel text-to-comic pipeline based on a text-to-image GAN that synthesizes comics according to text descriptions. 2. We describe an in-depth empirical study of the technical difficulties of comic generation using GAN's. ComicGAN has two novel features: (i) text description creation from labels via permutation and augmentation, and (ii) custom image encoding with Convolutional Neural Networks. We extensively evaluate the proposed ComicGAN in two scenarios, namely image generation from descriptions, and image generation from dialogue. Our results on 1000 Dilbert comic panels and 6000 descriptions show synthetic comic panels from text inputs resemble original Dilbert panels. Novel methods for text description creation and custom image encoding brought improvements to Frechet Inception Distance, detail, and overall image quality over baseline algorithms. Generating illustrations from descriptions provided clear comics including characters and colours that were specified in the descriptions.