Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[ICL+05]  Colorization by Example

Irony:2005:CE (In proceedings)
Author(s)Irony R., Cohen-Or D. and Lischinski D.
Title« Colorization by Example »
InProceedings of Eurographics Symposium on Rendering 2005 (EGSR'05, June 29--July 1, 2005, Konstanz, Germany)
Page(s)201--210
Year2005
PublisherEUROGRAPHICS
AddressAire-la-Ville, Switzerland

Abstract
We present a new method for colorizing grayscale images by transferring color from a segmented example image. Rather than relying on a series of independent pixel-level decisions, we develop a new strategy that attempts to account for the higher-level context of each pixel. The colorizations generated by our approach exhibit a much higher degree of spatial consistency, compared to previous automatic color transfer methods [WAM02]. We also demonstrate that our method requires considerably less manual effort than previous user-assisted colorization methods [LLW04]. Given a grayscale image to colorize, we first determine for each pixel which example segment it should learn its color from. This is done automatically using a robust supervised classification scheme that analyzes the low-level feature space defined by small neighborhoods of pixels in the example image. Next, each pixel is assigned a color from the appropriate region using a neighborhood matching metric, combined with spatial filtering for improved spatial coherence. Each color assignment is associated with a confidence value, and pixels with a sufficiently high confidence level are provided as “micro-scribbles” to the optimization-based colorization algorithm of Levin et al. [LLW04], which produces the final complete colorization of the image.

BibTeX code
@inproceedings{Irony:2005:CE,
  opteditor = {},
  optnote = {},
  optorganization = {},
  author = {Revital Irony and Daniel Cohen-Or and Dani Lischinski},
  optkey = {},
  optannote = {},
  optseries = {},
  address = EGAdr,
  localfile = {papers/Irony.2005.CE.pdf},
  publisher = EGPub,
  doi = {http://dx.doi.org/10.2312/EGWR/EGSR05/201-210},
  optmonth = {},
  optwww =
            {http://www.eg.org/EG/DL/WS/EGWR/EGSR05/201-210.pdf.abstract.pdf;internal&action=paperabstract.action},
  optcrossref = {},
  booktitle = {Proceedings of Eurographics Symposium on Rendering 2005 (EGSR'05,
               June 29--July 1, 2005, Konstanz, Germany)},
  optvolume = {},
  optnumber = {},
  abstract = {We present a new method for colorizing grayscale images by
              transferring color from a segmented example image. Rather than
              relying on a series of independent pixel-level decisions, we
              develop a new strategy that attempts to account for the
              higher-level context of each pixel. The colorizations generated by
              our approach exhibit a much higher degree of spatial consistency,
              compared to previous automatic color transfer methods [WAM02]. We
              also demonstrate that our method requires considerably less manual
              effort than previous user-assisted colorization methods [LLW04].
              Given a grayscale image to colorize, we first determine for each
              pixel which example segment it should learn its color from. This
              is done automatically using a robust supervised classification
              scheme that analyzes the low-level feature space defined by small
              neighborhoods of pixels in the example image. Next, each pixel is
              assigned a color from the appropriate region using a neighborhood
              matching metric, combined with spatial filtering for improved
              spatial coherence. Each color assignment is associated with a
              confidence value, and pixels with a sufficiently high confidence
              level are provided as “micro-scribbles” to the optimization-based
              colorization algorithm of Levin et al. [LLW04], which produces the
              final complete colorization of the image.},
  title = {{C}olorization by {E}xample},
  year = {2005},
  pages = {201--210},
}

 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!