Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[Kol05]  Image Segmentation for Stylized Non-Photorealistic Rendering and Animation

Kolliopoulos:2005:ISS (Master's thesis)
Author(s)Kolliopoulos A.
Title« Image Segmentation for Stylized Non-Photorealistic Rendering and Animation »
SchoolUniversity of Toronto, Department of Computer Science
Year2005
AddressCanada
URLhttp://www.cs.toronto.edu/DCS/Grad/Theses/04-05MSc.html#04-05alexk@dgp

Abstract
This thesis approaches the problem of non-photorealistic rendering by identifying segments in the image plane and filling them using algorithms to render in artistic styles. Using segments as a 2D primitive for non-photorealistic styles is a natural extension of techniques artists often implicitly employ for purposes such as abstraction of unnecessary detail. The problem of segmenting an arbitrary 3D scene in a 2D view using geometric scene information is presented, and a solution based on spectral clustering is proposed. With an acceleration technique, segmentation can be performed in near real-time for interactive, artistic environments. This approach is automatic beyond the setting of segmentation parameters by a user, and it can be extended to temporally coherent non-photorealistic animation by segmenting adjacent frames together. A number of artistic rendering styles are applied within this segmentation framework to demonstrate the effects that such a system makes possible.

BibTeX code
@mastersthesis{Kolliopoulos:2005:ISS,
  www = {http://www.dgp.toronto.edu/~alexk/segnpr.html},
  month = apr,
  author = {Alexander Kolliopoulos},
  optkey = {},
  optannote = {},
  opttype = {},
  url = {http://www.cs.toronto.edu/DCS/Grad/Theses/04-05MSc.html#04-05alexk@dgp},
  abstract = {This thesis approaches the problem of non-photorealistic rendering
              by identifying segments in the image plane and filling them using
              algorithms to render in artistic styles. Using segments as a 2D
              primitive for non-photorealistic styles is a natural extension of
              techniques artists often implicitly employ for purposes such as
              abstraction of unnecessary detail. The problem of segmenting an
              arbitrary 3D scene in a 2D view using geometric scene information
              is presented, and a solution based on spectral clustering is
              proposed. With an acceleration technique, segmentation can be
              performed in near real-time for interactive, artistic
              environments. This approach is automatic beyond the setting of
              segmentation parameters by a user, and it can be extended to
              temporally coherent non-photorealistic animation by segmenting
              adjacent frames together. A number of artistic rendering styles
              are applied within this segmentation framework to demonstrate the
              effects that such a system makes possible.},
  title = {{I}mage {S}egmentation for {S}tylized {N}on-{P}hotorealistic
           {R}endering and {A}nimation},
  school = {University of Toronto, Department of Computer Science},
  address = {Canada},
  localfile = {papers/Kolliopoulos.2005.ISS.pdf},
  year = {2005},
}

 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!