[JEG+02] Hatching by Example: a Statistical Approach

Tree

Index

NPR Literature

PREV NEXT

[JEG+02] Hatching by Example: a Statistical Approach

Jodoin:2002:HBE (In proceedings)
Author(s)	Jodoin P.M., Epstein E., Granger-Piché M. and Ostromoukhov V.
Title	« Hatching by Example: a Statistical Approach »
In	Proceedings of the Second International Symposium on Non-Photorealistic Animation and Rendering (NPAR 2002, Annecy, France, June 3--5, 2002)
Editor(s)	Adam Finkelstein
Page(s)	29--36
Year	2002
Publisher	ACM Press
Address	New York
Editor(s)	Adam Finkelstein

Abstract
We present a new approach to synthetic (computer-aided) drawing with patches of strokes. Grouped strokes convey the local intensity level that is desired in drawing. The key point of our approach is learning by example: the system does not know a priori the distribution of the strokes. Instead, by analyzing a sample (training) patch of strokes, our system is able to synthesize freely an arbitrary sequence of strokes that "looks like" the given sample. Strokes are considered as parametrical curves represented by a vector of random variables following a Markovian distribution. Our method is based on Shannon's N-gram approach and is a direct extension of Efros's texture synthesis models [EL99; EF01]. Nevertheless, one major difference between our method and traditional texture synthesis is the use of such curves as a basic element instead of pixels. We define a statistical metric for comparison between different patches containing various layouts of strokes. We hope that our method performs a first step towards capturing a very difficult notion of style in drawing --- hatching style in our case. We illustrate our method by varied examples, ranging from typical hatching in traditional drawing to highly heterogeneous sets of strokes.

Abstract

We present a new approach to synthetic (computer-aided) drawing with patches of strokes. Grouped strokes convey the local intensity level that is desired in drawing. The key point of our approach is learning by example: the system does not know a priori the distribution of the strokes. Instead, by analyzing a sample (training) patch of strokes, our system is able to synthesize freely an arbitrary sequence of strokes that "looks like" the given sample. Strokes are considered as parametrical curves represented by a vector of random variables following a Markovian distribution. Our method is based on Shannon's N-gram approach and is a direct extension of Efros's texture synthesis models [EL99; EF01]. Nevertheless, one major difference between our method and traditional texture synthesis is the use of such curves as a basic element instead of pixels. We define a statistical metric for comparison between different patches containing various layouts of strokes. We hope that our method performs a first step towards capturing a very difficult notion of style in drawing --- hatching style in our case. We illustrate our method by varied examples, ranging from typical hatching in traditional drawing to highly heterogeneous sets of strokes.

BibTeX code

@inproceedings{Jodoin:2002:HBE,
  optnote = {},
  optorganization = {},
  author = {Pierre-Marc Jodoin and Emric Epstein and Martin Granger-Pich{\'e}
            and Victor Ostromoukhov},
  optkey = {},
  optannote = {},
  optseries = {},
  editor = {Adam Finkelstein},
  address = {New York},
  localfile = {papers/Jodoin.2002.HBE.pdf },
  publisher = {ACM Press},
  doi = {http://doi.acm.org/10.1145/508530.508536},
  optmonth = {},
  citeseer = {http://citeseer.nj.nec.com/jodoin02hatching.html},
  optcrossref = {},
  booktitle = NPAR2002,
  optstatus = {OK},
  optvolume = {},
  optnumber = {},
  title = {{H}atching by {E}xample: a {S}tatistical {A}pproach},
  abstract = {We present a new approach to synthetic (computer-aided) drawing
              with patches of strokes. Grouped strokes convey the local
              intensity level that is desired in drawing. The key point of our
              approach is learning by example: the system does not know a priori
              the distribution of the strokes. Instead, by analyzing a sample
              (training) patch of strokes, our system is able to synthesize
              freely an arbitrary sequence of strokes that "looks like" the
              given sample. Strokes are considered as parametrical curves
              represented by a vector of random variables following a Markovian
              distribution. Our method is based on Shannon's N-gram approach and
              is a direct extension of Efros's texture synthesis models [EL99;
              EF01]. Nevertheless, one major difference between our method and
              traditional texture synthesis is the use of such curves as a basic
              element instead of pixels. We define a statistical metric for
              comparison between different patches containing various layouts of
              strokes. We hope that our method performs a first step towards
              capturing a very difficult notion of style in drawing --- hatching
              style in our case. We illustrate our method by varied examples,
              ranging from typical hatching in traditional drawing to highly
              heterogeneous sets of strokes. },
  year = {2002},
  pages = {29--36},
}

Overview

Tree

Index

NPR Literature

PREV NEXT

FRAMES NO FRAME

Submit a bug