Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[SBH+04]  Unsupervised Colorization of Black-and-White Cartoons

Sykora:2004:UCB (In proceedings)
Author(s)Sýkora D., Buriánek J. and HASH(0x897b1ac)Zára J.
Title« Unsupervised Colorization of Black-and-White Cartoons »
InProceedings of the Third International Symposium on Non-Photorealistic Animation and Rendering (NPAR 2004, Annecy, France, June 7--9, 2004)
Editor(s)Aaron Hertzmann and Craig Kaplan
Page(s)121--128
Year2004
PublisherACM Press
AddressNew York
Editor(s)Aaron Hertzmann and Craig Kaplan

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.

BibTeX code
@inproceedings{Sykora:2004:UCB,
  optorganization = {},
  author = {Daniel S{\'{y}}kora and Jan Buri{\'{a}}nek and Ji{\v{r}}{\'{\i}}
            {\v{Z}}{\'{a}}ra},
  optkey = {},
  optseries = {},
  editor = {Aaron Hertzmann and Craig Kaplan},
  localfile = {papers/Sykora.2004.UCB.pdf},
  address = {New York},
  publisher = {ACM Press},
  optmonth = {},
  doi = {http://doi.acm.org/10.1145/987657.987677},
  opturl = {},
  optwww = {},
  optcrossref = {},
  booktitle = NPAR2004,
  optstatus = {},
  optvolume = {},
  optnumber = {},
  title = {{U}nsupervised {C}olorization of {B}lack-and-{W}hite {C}artoons},
  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.},
  year = {2004},
  pages = {121--128},
}

 Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

Submit a bug

This document was generated by bib2html 3.3.
Copyright © 1998-05 Stéphane GALLAND (under the GNU General Public License)

Valid HTML 4.01!Valid CSS!