Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN

TL;DR

This paper introduces a novel neural network approach combining Residual U-net and AC-GAN to achieve automatic, high-quality style transfer and colorization for anime sketches, overcoming limitations of existing methods.

Contribution

It presents an integrated Residual U-net and AC-GAN framework specifically designed for anime sketch style transfer, improving accuracy and efficiency.

Findings

High-quality style transfer achieved on anime sketches

Automatic and fast processing pipeline

Superior colorization and style fidelity

Abstract

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.