Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[WOG+06]  Real-Time Video Abstraction

Winnemoeller:2006:RTV (Article)
Author(s)Winnemöller H., Olsen S. and Gooch B.
Title« Real-Time Video Abstraction »
JournalACM Transactions on Graphics, Proceedings of ACM SIGGRAPH 2006 (Boston, MA, July 30--August 3, 2006)
Volume25
Number3
Page(s)1221--1226
Year2006
URLhttp://www.videoabstraction.net/

Abstract
We present an automatic, real-time video and image abstraction framework that abstracts imagery by modifying the contrast of visually important features, namely luminance and color opponency. We reduce contrast in low-contrast regions using an approximation to anisotropic diffusion, and artificially increase contrast in higher contrast regions with difference-of-Gaussian edges. The abstraction step is extensible and allows for artistic or data-driven control. Abstracted images can optionally be stylized using soft color quantization to create cartoon-like effects with good temporal coherence. Our framework design is highly parallel, allowing for a GPU-based, real-time implementation. We evaluate the effectiveness of our abstraction framework with a user-study and find that participants are faster at naming abstracted faces of known persons compared to photographs. Participants are also better at remembering abstracted images of arbitrary scenes in a memory task.

BibTeX code
@article{Winnemoeller:2006:RTV,
  optpostscript = {},
  number = {3},
  month = jul,
  author = {Holger Winnem{\"o}ller and Sven C. Olsen and Bruce Gooch},
  optkey = {},
  optannote = {},
  url = {http://www.videoabstraction.net/},
  localfile = {papers/Winnemoeller.2006.RTV.pdf},
  optkeywords = {},
  doi = {http://doi.acm.org/10.1145/1141911.1142018},
  optciteseer = {},
  journal = SIGGRAPH2006,
  volume = {25},
  optwww = {},
  title = {{R}eal-{T}ime {V}ideo {A}bstraction},
  abstract = {We present an automatic, real-time video and image abstraction
              framework that abstracts imagery by modifying the contrast of
              visually important features, namely luminance and color opponency.
              We reduce contrast in low-contrast regions using an approximation
              to anisotropic diffusion, and artificially increase contrast in
              higher contrast regions with difference-of-Gaussian edges. The
              abstraction step is extensible and allows for artistic or
              data-driven control. Abstracted images can optionally be stylized
              using soft color quantization to create cartoon-like effects with
              good temporal coherence. Our framework design is highly parallel,
              allowing for a GPU-based, real-time implementation. We evaluate
              the effectiveness of our abstraction framework with a user-study
              and find that participants are faster at naming abstracted faces
              of known persons compared to photographs. Participants are also
              better at remembering abstracted images of arbitrary scenes in a
              memory task.},
  pages = {1221--1226},
  year = {2006},
}

 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!