Colorization of black-and-white cartoons

摘要

We introduce a novel colorization framework for old black-and-white cartoons originally produced by a cel or paper based technology. In this case, the dynamic part of the scene is represented by a set of outlined homogeneous regions which superimpose the static background. To reduce a large amount of manual intervention we combine unsupervised image segmentation, background reconstruction, and structural prediction. Our system allows the user to specify the brightness of applied colors unlike the most of previous approaches which operate only with hue and saturation. We also present simple but effective color modulation, composition and dust spot removal techniques able to produce color images in broadcast quality without additional user intervention.