Unsupervised Colorization of Black-and-White Cartoons
Author(s): Daniel Sýkora, Jan Buriánek, Jiří Žára.
Proceedings: 3rd International Symposium on Non-Photorealistic Animation and Rendering (NPAR'04), pp. 121--127, Annecy, France, June,
2004.
[BibTeX] 
Abstract:
We present a novel color-by-example technique which combines
image segmentation, patch-based sampling and probabilistic reasoning.
This method is able to automate movie colorization when
new color information is applied on the already designed black-andwhite
cartoon. Our technique is especially suitable for cartoons digitized
from classical celluloid movies, which have been originally
produced by a paper or foil based method. In this case, the background
is a static image whilst only the dynamic foreground needs
to be colored frame-by-frame. We also assume that objects in the
foreground layer consist of several well visible outlines which will
emphasize the shape of homogeneous regions.