Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[CH+03]  Cubist Style Rendering from Photographs

Collomosse:2003:CSR (Article)
Author(s)Collomosse J. and Hall P.
Title« Cubist Style Rendering from Photographs »
JournalIEEE Transactions on Visualization and Computer Graphics
Volume9
Number4
Page(s)443--453
Year2003
URLhttp://www.cs.bath.ac.uk/~jpc/research.htm#cubist

Abstract
The contribution of this paper is a novel non-photorealistic rendering (NPR) technique, influenced by the style of Cubist art. Specifically we are motivated by artists such as Picasso and Braque, who produced art work by composing elements of a scene taken from multiple points of view; paradoxically such compositions convey a sense of motion without assuming temporal dependence between views. Our method accepts a set of two-dimensional images as input, and produces a Cubist style painting with minimal user interaction. We use salient features identified within the image set, such as eyes, noses and mouths as compositional elements; we believe the use of such features to be a unique contribution to NPR. Before composing features into a final image we geometrically distort them to produce the more angular forms common in Cubist art. Finally we render the composition to give a painterly effect, using an automatic algorithm. This paper describes our method, illustrating the application of our algorithm with a gallery of images. We conclude with a critical appraisal and suggest the use of ``high-level'' features is of interest to NPR.

BibTeX code
@article{Collomosse:2003:CSR,
  citeseer = {http://citeseer.nj.nec.com/597220.html},
  number = {4},
  volume = {9},
  month = {oct--dec},
  author = {John P. Collomosse and Peter M. Hall},
  optkey = {},
  optstatus = {},
  url = {http://www.cs.bath.ac.uk/~jpc/research.htm#cubist},
  localfile = {papers/Collomosse.2003.CSR.pdf},
  abstract = {The contribution of this paper is a novel non-photorealistic
              rendering (NPR) technique, influenced by the style of Cubist art.
              Specifically we are motivated by artists such as Picasso and
              Braque, who produced art work by composing elements of a scene
              taken from multiple points of view; paradoxically such
              compositions convey a sense of motion without assuming temporal
              dependence between views. Our method accepts a set of
              two-dimensional images as input, and produces a Cubist style
              painting with minimal user interaction. We use salient features
              identified within the image set, such as eyes, noses and mouths as
              compositional elements; we believe the use of such features to be
              a unique contribution to NPR. Before composing features into a
              final image we geometrically distort them to produce the more
              angular forms common in Cubist art. Finally we render the
              composition to give a painterly effect, using an automatic
              algorithm. This paper describes our method, illustrating the
              application of our algorithm with a gallery of images. We conclude
              with a critical appraisal and suggest the use of ``high-level''
              features is of interest to NPR.},
  title = {{C}ubist {S}tyle {R}endering from {P}hotographs},
  doi = {http://dx.doi.org/10.1109/TVCG.2003.1260739},
  journal = j-IEEE-VCG,
  year = {2003},
  pages = {443--453},
}

 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!