• DocumentCode
    1234527
  • Title

    Fast texture transfer

  • Author

    Ashikhmin, Michael

  • Author_Institution
    Comput. Sci. Dept., Stony Brook Univ., NY, USA
  • Volume
    23
  • Issue
    4
  • fYear
    2003
  • Firstpage
    38
  • Lastpage
    43
  • Abstract
    The article presents an algorithm for texture transfer between images that is up to several orders of magnitude faster than current state-of-the-art techniques. I demonstrate how the technique can leverage self-similarity of complex images to increase resolution of some types of images and to create novel, artistic looking images from photographs without any prior artistic source. Compared to other alternatives, methods based on texture transfer are global in the sense that the user need not deal with details such as defining and painting individual brush strokes. Texture transfer methods are also more general since they don´t need to emulate any particular artistic style (line drawing, hatching, realistic oil painting, and so on). Not surprisingly, there is a price to pay for this generality - an algorithm designed for a specific artistic style will most likely produce results superior to those presented in the paper for that particular case.
  • Keywords
    image enhancement; image resolution; image texture; rendering (computer graphics); algorithm; artistic style transfer; complex images; fast texture transfer; image enhancement; nonphotorealistic filter creation; photographs; resolution; self similarity; Computational efficiency; Convergence; Costs; Degradation; Difference equations; Feedback; Filtering; Large-scale systems; Particle measurements; Pixel;
  • fLanguage
    English
  • Journal_Title
    Computer Graphics and Applications, IEEE
  • Publisher
    ieee
  • ISSN
    0272-1716
  • Type

    jour

  • DOI
    10.1109/MCG.2003.1210863
  • Filename
    1210863