Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[GGD+05]  Stylized Rendering for Multiresolution Image Representation

Grundland:2005:SRM (In proceedings)
Author(s)Grundland M., Gibbs C. and Dodgson N.
Title« Stylized Rendering for Multiresolution Image Representation »
InHuman Vision and Electronic Imaging X Conference (January 17--20, 2005, San Jose, USA)
SeriesSPIE Proceedings Series
Editor(s)Bernice E. Rogowitz and Thrasyvoulos N. Pappas and Scott J. Daly
Volume5666
Page(s)280--292
Year2005
PublisherSPIE/IS&T
AddressBellingham, Washington
URLhttp://www.cl.cam.ac.uk/~mg290/Portfolio/StylizedRendering.html
Editor(s)Bernice E. Rogowitz and Thrasyvoulos N. Pappas and Scott J. Daly

Abstract
By integrating stylized rendering with an efficient multiresolution image representation, we enable the user to control how compression affects the aesthetic appearance of an image. Adopting a point-based rendering approach to progressive image transmission and compression, we represent an image by a sequence of color values. To best approximate the image at progressive levels of detail, a novel, adaptive farthest point sampling algorithm balances global coverage with local precision. Without storing any spatial information apart from the aspect ratio, the spatial position of each color value is inferred from the preceding members of the sampling sequence. Keeping track of the spatial influence of each sample on the rendition, a progressively generated discrete Voronoi diagram forms the common foundation for our sampling and rendering framework. This framework allows us to extend traditional photorealistic methods of image reconstruction by scattered data interpolation to encompass non-photorealistic rendering. It supports a wide variety of artistic rendering styles based on geometric subdivision or parametric procedural textures. Genetic programming enables the user to create original rendering styles through interactive evolution by aesthetic selection. Comparing our results with JPEG, we conclude with a brief overview of the implications of using non-photorealistic representations for highly compressed imagery.

BibTeX code
@inproceedings{Grundland:2005:SRM,
  optpostscript = {},
  optorganization = {},
  author = {Mark Grundland and Chris Gibbs and Neil A. Dodgson},
  optkey = {},
  series = {SPIE Proceedings Series},
  optannote = {},
  editor = {Bernice E. Rogowitz and Thrasyvoulos N. Pappas and Scott J. Daly},
  url = {http://www.cl.cam.ac.uk/~mg290/Portfolio/StylizedRendering.html},
  address = {Bellingham, Washington},
  localfile = {papers/Grundland.2005.SRM.pdf},
  optisbn = {},
  publisher = {SPIE/IS\&T},
  optkeywords = {},
  optmonth = {},
  optciteseer = {},
  doi = {http://dx.doi.org/10.1117/12.596817},
  volume = {5666},
  optcrossref = {},
  optwww = {},
  booktitle = {Human Vision and Electronic Imaging X Conference (January 17--20,
               2005, San Jose, USA)},
  optnumber = {},
  abstract = {By integrating stylized rendering with an efficient
              multiresolution image representation, we enable the user to
              control how compression affects the aesthetic appearance of an
              image. Adopting a point-based rendering approach to progressive
              image transmission and compression, we represent an image by a
              sequence of color values. To best approximate the image at
              progressive levels of detail, a novel, adaptive farthest point
              sampling algorithm balances global coverage with local precision.
              Without storing any spatial information apart from the aspect
              ratio, the spatial position of each color value is inferred from
              the preceding members of the sampling sequence. Keeping track of
              the spatial influence of each sample on the rendition, a
              progressively generated discrete Voronoi diagram forms the common
              foundation for our sampling and rendering framework. This
              framework allows us to extend traditional photorealistic methods
              of image reconstruction by scattered data interpolation to
              encompass non-photorealistic rendering. It supports a wide variety
              of artistic rendering styles based on geometric subdivision or
              parametric procedural textures. Genetic programming enables the
              user to create original rendering styles through interactive
              evolution by aesthetic selection. Comparing our results with JPEG,
              we conclude with a brief overview of the implications of using
              non-photorealistic representations for highly compressed
              imagery.},
  title = {{S}tylized {R}endering for {M}ultiresolution {I}mage
           {R}epresentation},
  year = {2005},
  pages = {280--292},
}

 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!