Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
This addresses a domain-specific issue for anime artists and enthusiasts, offering an incremental improvement over existing style transfer methods.
The paper tackled the problem of applying painting styles to anime sketches, which existing neural style transfer methods fail to do by randomly colorizing lines, and achieved automatic, fast, and creditable results in art style and colorization.
Recently, with the revolutionary neural style transferring methods, creditable paintings can be synthesized automatically from content images and style images. However, when it comes to the task of applying a painting's style to an anime sketch, these methods will just randomly colorize sketch lines as outputs and fail in the main task: specific style tranfer. In this paper, we integrated residual U-net to apply the style to the gray-scale sketch with auxiliary classifier generative adversarial network (AC-GAN). The whole process is automatic and fast, and the results are creditable in the quality of art style as well as colorization.