GANime: Generating Anime and Manga Character Drawings from Sketches with Deep Learning
This addresses a costly bottleneck in the manga and anime industry, but it is incremental as it compares existing methods.
The study tackled the problem of generating fully colorized anime and manga character drawings from sketches, finding that C-GAN was the most effective model for producing high-quality, high-resolution images close to human-created ones.
The process of generating fully colorized drawings from sketches is a large, usually costly bottleneck in the manga and anime industry. In this study, we examine multiple models for image-to-image translation between anime characters and their sketches, including Neural Style Transfer, C-GAN, and CycleGAN. By assessing them qualitatively and quantitatively, we find that C-GAN is the most effective model that is able to produce high-quality and high-resolution images close to those created by humans.