@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},
}
|