Painting Style-Aware Manga Colorization Based on Generative Adversarial Networks
This addresses the high labor costs of manual colorization for manga creators, though it is incremental as it builds on existing GAN methods for a specific domain.
The paper tackles the problem of automatically colorizing manga comics while maintaining consistent painting style across consecutive images, using a GAN-based semi-automatic method that learns from small training data, and it achieves better performance than existing alternatives.
Japanese comics (called manga) are traditionally created in monochrome format. In recent years, in addition to monochrome comics, full color comics, a more attractive medium, have appeared. Unfortunately, color comics require manual colorization, which incurs high labor costs. Although automatic colorization methods have been recently proposed, most of them are designed for illustrations, not for comics. Unlike illustrations, since comics are composed of many consecutive images, the painting style must be consistent. To realize consistent colorization, we propose here a semi-automatic colorization method based on generative adversarial networks (GAN); the method learns the painting style of a specific comic from small amount of training data. The proposed method takes a pair of a screen tone image and a flat colored image as input, and outputs a colorized image. Experiments show that the proposed method achieves better performance than the existing alternatives.