Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[Her01b]  Paint By Relaxation

Hertzmann:2001:PBR (In proceedings)
Author(s)Hertzmann A.
Title« Paint By Relaxation »
InProceedings Computer Graphics International 2001 (Hong Kong, jul 2001)
Editor(s)Horace H. S. Ip and Nadia Magnenat-Thalmann and Tat-Seng Chua Rynson W. H. Lau
Page(s)47--54
Year2001
PublisherIEEE Computer Society
AddressLos Alamitos, CA
Editor(s)Horace H. S. Ip and Nadia Magnenat-Thalmann and Tat-Seng Chua Rynson W. H. Lau

Abstract
We use relaxation to produce painted imagery from images and video. An energy function is first specified; we then search for a painting with minimal energy. The appeal of this strategy is that, ideally, we need only specify what we want, not how to directly compute it. Because the energy function is very difficult to optimize, we use a relaxation algorithm combined with search heuristics. This formulation allows us to specify painting style by varying the relative weights of energy terms. The basic energy function yields an economical style that conveys an image with few strokes. This style produces greater temporal coherence for video than previous techniques. The system allows as fine user control as desired: the user may interactively change the painting style, specify variations of style over an image, and/or add specific strokes to the painting.

BibTeX code
@inproceedings{Hertzmann:2001:PBR,
  optnote = {},
  optorganization = {},
  author = {Aaron Hertzmann},
  optkey = {},
  optannote = {},
  optseries = {},
  editor = {Horace H. S. Ip and Nadia Magnenat-Thalmann and Tat-Seng Chua Rynson
            W. H. Lau},
  address = IEEEAdr,
  localfile = {papers/Hertzmann.2001.PBR.pdf},
  publisher = IEEEPub,
  doi = {http://dx.doi.org/10.1109/CGI.2001.934657},
  optmonth = {},
  citeseer = {http://citeseer.nj.nec.com/hertzmann01paint.html},
  optcrossref = {},
  booktitle = {Proceedings Computer Graphics International 2001 (Hong Kong, jul
               2001)},
  optstatus = {doi},
  optvolume = {},
  optnumber = {},
  title = {{P}aint {B}y {R}elaxation},
  abstract = {We use relaxation to produce painted imagery from images and
              video. An energy function is first specified; we then search for a
              painting with minimal energy. The appeal of this strategy is that,
              ideally, we need only specify what we want, not how to directly
              compute it. Because the energy function is very difficult to
              optimize, we use a relaxation algorithm combined with search
              heuristics. This formulation allows us to specify painting style
              by varying the relative weights of energy terms. The basic energy
              function yields an economical style that conveys an image with few
              strokes. This style produces greater temporal coherence for video
              than previous techniques. The system allows as fine user control
              as desired: the user may interactively change the painting style,
              specify variations of style over an image, and/or add specific
              strokes to the painting. },
  year = {2001},
  pages = {47--54},
}

 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!