• DocumentCode
    678737
  • Title

    Parameter optimisation for texture completion

  • Author

    Nguyen, Hien M. ; Wunsche, Burkhard C. ; Delmas, Patrice ; Lutteroth, C.

  • Author_Institution
    Dept. of Comput. Sci., Univ. of Auckland, Auckland, New Zealand
  • fYear
    2013
  • fDate
    27-29 Nov. 2013
  • Firstpage
    226
  • Lastpage
    230
  • Abstract
    In 3D reconstruction applications frequently large mesh sections are missing. While the geometry can be created with mesh completion techniques, reconstructing the texture is more difficult. An exemplar-based synthesis usually requires that the missing region contains only one texture pattern. Image inpainting techniques work for more complex textures, but were designed primarily to fill narrow missing regions and tend to produce undesirable results when the missing region is large. We solve this problem by exploiting the fact that most 3D objects contain different surface regions with similar textures. We use an appearance space to identify suitable texture patches fitting with the boundary of the missing region, and fill the region by using a patch-based synthesis combined with Poisson interpolation. We evaluate the effect of different parameters and demonstrate its improved performance over existing inpainting techniques.
  • Keywords
    image reconstruction; image texture; interpolation; mesh generation; optimisation; stochastic processes; 3D reconstruction applications; Poisson interpolation; exemplar-based synthesis; image inpainting techniques; mesh completion techniques; parameter optimisation; patch-based synthesis; surface regions; texture completion; texture patches; texture pattern; texture reconstruction; Image color analysis; Image reconstruction; Interpolation; Surface reconstruction; Surface texture; Three-dimensional displays; Vectors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image and Vision Computing New Zealand (IVCNZ), 2013 28th International Conference of
  • Conference_Location
    Wellington
  • ISSN
    2151-2191
  • Print_ISBN
    978-1-4799-0882-0
  • Type

    conf

  • DOI
    10.1109/IVCNZ.2013.6727020
  • Filename
    6727020