Deep Manga Colorization with Color Style Extraction by Conditional Adversarially Learned Inference

Abstract

Many comic books are now published as digital books, which easily provide colored contents compared to physical books. The motivation of automatic colorization of comic books now arises. Previous studies colorize sketches with spatial color annotations or no clues at all. They are expected to reduce workloads of comic artists but still require spatial color annotations in order to produce desirable colorizations. This study introduces color style information and combines it with the conditional adversarially learned inference. Experimental results demonstrate that objects in the manga are painted with colors depending on color style information and that color style information extracted from another colored image to paint an object with the desired color.