• DocumentCode
    2712042
  • Title

    Refractive height fields from single and multiple images

  • Author

    Shan, Qi ; Agarwal, Sameer ; Curless, Brian

  • Author_Institution
    Univ. of Washington, Seattle, WA, USA
  • fYear
    2012
  • fDate
    16-21 June 2012
  • Firstpage
    286
  • Lastpage
    293
  • Abstract
    We propose a novel framework for reconstructing homogenous, transparent, refractive height-fields from a single viewpoint. The height-field is imaged against a known planar background, or sequence of backgrounds. Unlike existing approaches that do a point-by-point reconstruction - which is known to have intractable ambiguities - our method estimates and optimizes for the entire height-field at the same time. The formulation supports shape recovery from measured distortions (deflections) or directly from the images themselves, including from a single image. We report results for a variety of refractive height-fields showing significant improvement over prior art.
  • Keywords
    computer vision; image reconstruction; computer vision; homogenous height-fields; multiple images; point-by-point reconstruction; refractive height fields; refractive height-fields; shape recovery; single images; transparent height-fields; Cameras; Glass; Image reconstruction; Indexes; Optimization; Shape; Surface reconstruction;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
  • Conference_Location
    Providence, RI
  • ISSN
    1063-6919
  • Print_ISBN
    978-1-4673-1226-4
  • Electronic_ISBN
    1063-6919
  • Type

    conf

  • DOI
    10.1109/CVPR.2012.6247687
  • Filename
    6247687