Proceedings: GI 2007

Optimized tile-based texture synthesis

Weiming Dong , Ning Zhou , Jean-Claude Paul

Proceedings of Graphics Interface 2007: Montréal, Québec, Canada, 28 - 30 May 2007, 249-256

DOI 10.20380/GI2007.33

  • Bibtex

    @inproceedings{Dong:2007:10.20380/GI2007.33,
    author = {Dong, Weiming and Zhou, Ning and Paul, Jean-Claude},
    title = {Optimized tile-based texture synthesis},
    booktitle = {Proceedings of Graphics Interface 2007},
    series = {GI 2007},
    year = {2007},
    issn = {0713-5424},
    isbn = {978-1-56881-337-0},
    location = {Montr{\'e}al, Qu{\'e}bec, Canada},
    pages = {249--256},
    numpages = {8},
    doi = {10.20380/GI2007.33},
    acmdoi = {doi>10.1145/1268517.1268558},
    publisher = {Canadian Human-Computer Communications Society},
    address = {University of Waterloo, Waterloo, Ontario, Canada},
    }

Abstract

One significant problem in tile-based texture synthesis is the presence of conspicuous seams in the tiles. The reason is that the sample patches employed as primary patterns of the tile set may not be well stitched if carelessly picked. In this paper, we introduce an optimized approach that can stably generate an ω-tile set of high pattern diversity and high quality. Firstly, an extendable rule is introduced to increase the number of sample patches to vary the patterns in an ω-tile set. Secondly, in contrast to the other concurrent techniques that randomly choose sample patches for tile construction, our technique uses Genetic Algorithm to select the feasible patches from the input example. This operation insures the quality of the whole tile set. Experimental results verify the high quality and efficiency of the proposed algorithm.