Procedural 3D Texture Synthesis Using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@Article{hewgill:2004:CG,
  author =       "Adam Hewgill and Brian J. Ross",
  title =        "Procedural {3D} Texture Synthesis Using Genetic
                 Programming",
  journal =      "Computers and Graphics",
  year =         "2004",
  volume =       "28",
  number =       "4",
  pages =        "569--584",
  month =        aug,
  keywords =     "genetic algorithms, genetic programming, Procedural
                 textures, Evolution, grammar BNF",
  URL =          "http://www.cosc.brocku.ca/~bross/research/HewgillRoss04.pdf",
  URL =          "http://www.sciencedirect.com/science/article/B6TYG-4CS4FCT-1/2/b8a5d381a1371ba6545d194a470dfa89",
  ISSN =         "0097-8493",
  DOI =          "doi:10.1016/j.cag.2004.04.012",
  abstract =     "The automatic synthesis of procedural textures for 3D
                 surfaces using genetic programming is investigated.
                 Genetic algorithms employ a search strategy inspired by
                 Darwinian natural evolution. Genetic programming uses
                 genetic algorithms on tree structures, which are
                 interpretable as computer programs or mathematical
                 formulae. We define a texture generation language in
                 the genetic programming system, which is then used to
                 evolve textures having particular characteristics of
                 interest. The texture generation language used here
                 includes operators useful for texture creation, for
                 example, mathematical operators, colour functions and
                 noise functions. In order to be practical for 3D model
                 rendering, the language includes primitives that access
                 surface information for the point being rendered, such
                 as coordinates values, normal vectors, and surface
                 gradients. A variety of experiments successfully
                 generated procedural textures that displayed visual
                 characteristics similar to the target textures used
                 during training.",
  notes =        "\cite{hewgill:2003:06} is prelimary version. lilgp.
                 Ten runs in parallel on 16-CPU Silicon Graphics Origin
                 2000 server. Fig 9 Woman's clothing training points",
}

Genetic Programming entries for Adam Hewgill Brian J Ross

Citations