• DocumentCode
    3050791
  • Title

    Merging ratio images based realistic object class re-rendering

  • Author

    Yun, Fu

  • Author_Institution
    Inst. of Artificial Intelligence & Robotics, Xi´´an Jiaotong Univ., China
  • Volume
    5
  • fYear
    2004
  • fDate
    24-27 Oct. 2004
  • Firstpage
    3523
  • Abstract
    The merging ratio image (MRI) for realistic object class re-rendering is presented and applied to human face image. We focus on the Lambertian object class and utilize a uniform ratio image scheme - merging ratio image - to merge the expression ratio image, ageing ratio image, and illumination ratio image (quotient image), which exhibits a new facial model quality. Given a single face image and some other photorealistic face examples with distinct attributes, such as aged wrinkles, expressive feature motions, and certain lighting conditions, we generate expressive expressions, natural ageing, rejuvenating and varying illuminations with MRI rendering technique. Experimental results demonstrate the attractive properties of our method with some face examples from MPI Caucasian face database and AI&R Asian face database.
  • Keywords
    image processing; lighting; rendering (computer graphics); visual databases; Caucasian face database; Lambertian object class; aged wrinkles; ageing ratio image; expression ratio image; expressive expressions; expressive feature motions; facial model quality; human face image; illumination ratio image; merging ratio images; natural ageing; realistic object class rerendering; rejuvenating; rendering technique; uniform ratio image scheme; varying illuminations; Aging; Face; Humans; Image databases; Lighting; Magnetic resonance imaging; Merging; Reflectivity; Rendering (computer graphics); Spatial databases;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 2004. ICIP '04. 2004 International Conference on
  • ISSN
    1522-4880
  • Print_ISBN
    0-7803-8554-3
  • Type

    conf

  • DOI
    10.1109/ICIP.2004.1421876
  • Filename
    1421876