3532 articles – 5253 references  [version française]

inria-00152395, version 1

Optimal Sample Patches Selection for Tile-Based Texture Synthesis

Weiming Dong () a, 1, Shuangxian Sun b, 2, Jean-Claude Paul () a, 3

9th International CAD/Graphics 2005 (2005)

Abstract: One significant problem in tile-based texture synthesis is the selection of sample patches. The reason is that the tiling process may produce results with poor quality when the sample patches used to fill the tiles can not find good cutting pathes at the merging stage. In this paper, we use Genetic Algorithm to find the best group of sample patches from a considerable number of patch groups. Using tile set gene rated by these optimal sample patches can significantly improve the result quality of the tile-based texture synthesis.

  • a –  INRIA
  • b –  Beijing Jiaotong University
  • 1:  ALICE (INRIA Lorraine - LORIA)
  • INRIA – CNRS : UMR7503 – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)
  • 2:  School of Mathematics (SCHOOL OF MATHEMATICS)
  • Beijing Jiaotong University
  • 3:  CAD (CAD LIAMA INRIA Paris - Rocquencourt)
  • Centre de coopération internationale en recherche agronomique pour le développement [CIRAD] – CNRS – Institut national de la recherche agronomique (INRA) – Chinese Academy of Science (CAS) – Institute of Automation, Chinese Academy of Sciences – INRIA
  • Domain : Computer Science/Computer Graphics and Virtual Reality
  • Keywords : Genetic Algorithm – Tile-Based Texture Synthesis – Wang Tiles – Image Quilting
 
  • inria-00152395, version 1
  • http://hal.inria.fr/inria-00152395
  • oai:hal.inria.fr:inria-00152395
  • From: Weiming Dong <>
  • Submitted on: Wednesday, 6 June 2007 16:42:53
  • Updated on: Wednesday, 26 September 2007 15:27:46