Overview   Tree   Index 
NPR Literature
PREV  NEXT FRAMES  NO FRAME 

[FTP+99]  An Example-Based Approach to Style Translation for Line Drawings

Freeman:1999:AEB (Technical report)
Author(s)Freeman W., Tenenbaum J. and Pasztor E.
Title« An Example-Based Approach to Style Translation for Line Drawings »
NumberTR-99-11
InstitutionMERL -- A Mitsubishi Electric Research Laboratory
Year1999
URLhttp://www.merl.com/papers/docs/TR99-11.pdf

Abstract
training set of many different lines, each drawn by an artist in various styles, which is used to translate new lines made by a user into a particular desired style with a it K-nearest neighbor algorithm. This algorithm fits each input line as a linear combination of the several training lines in the same style which are most similar to it. The fit line can then be rendered in different styles because the training set contains versions of each training line in each style. By describing input lines as linear combinations of training set lines, this procedure is expressive enough to fit a broad range of input drawings. By restricting these linear combinations to contain only the most similar training set lines, this procedure is constrained enough to preserve the distinctive stylistic features of translated lines. We represent input lines by splines with nonuniformly spaced control points, which emphasizes these stylistic features. Our example-based approach has a number of advantages over conventional parameteric approaches to translating style. It can handle styles which are difficult to describe parametrically, and its repertoire can be easily extended by the user at any time. Moreover, given appropriate representations, it can be generalized to modify the style of other kinds of graphics objects, such as the font of a letter or the movement style of an animated character.

BibTeX code
@techreport{Freeman:1999:AEB,
  number = {TR-99-11},
  optnote = {},
  optaddress = {},
  author = {William T. Freeman and Joshua B. Tenenbaum and Egon Pasztor},
  optkey = {},
  optannote = {},
  opttype = {},
  url = {http://www.merl.com/papers/docs/TR99-11.pdf},
  localfile = {papers/Freeman.1999.AEB.pdf},
  optmonth = {},
  optdoi = {},
  optstatus = {doi},
  abstract = {training set of many different lines, each drawn by an artist in
              various styles, which is used to translate new lines made by a
              user into a particular desired style with a {it K-nearest
              neighbor} algorithm. This algorithm fits each input line as a
              linear combination of the several training lines in the same style
              which are most similar to it. The fit line can then be rendered in
              different styles because the training set contains versions of
              each training line in each style. By describing input lines as
              linear combinations of training set lines, this procedure is
              expressive enough to fit a broad range of input drawings. By
              restricting these linear combinations to contain only the most
              similar training set lines, this procedure is constrained enough
              to preserve the distinctive stylistic features of translated
              lines. We represent input lines by splines with nonuniformly
              spaced control points, which emphasizes these stylistic features.
              Our example-based approach has a number of advantages over
              conventional parameteric approaches to translating style. It can
              handle styles which are difficult to describe parametrically, and
              its repertoire can be easily extended by the user at any time.
              Moreover, given appropriate representations, it can be generalized
              to modify the style of other kinds of graphics objects, such as
              the font of a letter or the movement style of an animated
              character.},
  title = {{A}n {E}xample-{B}ased {A}pproach to {S}tyle {T}ranslation for {L}ine
           {D}rawings},
  institution = {MERL -- A Mitsubishi Electric Research Laboratory},
  year = {1999},
}

 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!