• DocumentCode
    123398
  • Title

    Improved radial basis function based parameterization for facial expression animation

  • Author

    Zhida Li ; Ji Ma ; Hsi-Yung Feng

  • Author_Institution
    Dept. of Mech. Eng., Univ. of British Columbia, Vancouver, BC, Canada
  • fYear
    2014
  • fDate
    22-24 Aug. 2014
  • Firstpage
    341
  • Lastpage
    346
  • Abstract
    This paper presents an improved method for facial expression animation based on the radial basis functions. The existing facial action coding system is adopted for expression parameterization. A set of parameters that are able to generate proper expressions is carefully selected through a series of analyses and comparisons. A deformation algorithm combining compactly supported radial basis functions with a geodesic distance metric is employed to address the difficulties in generating facial expressions, such as localized deformation and hole handling. In this work, the complex manipulation of a 3D face mesh is transformed into simple linear parameter adjustments, which is intuitive and efficient. Implementation results have demonstrated that real-time interactive mesh modification for facial expression animation is achieved.
  • Keywords
    computational geometry; computer animation; mesh generation; radial basis function networks; 3D face mesh manipulation; compactly supported radial basis functions; deformation algorithm; facial action coding system; facial expression animation; facial expression parameterization; geodesic distance metric; hole handling; linear parameter adjustments; localized deformation; radial basis function based parameterization; real-time interactive mesh modification; Computers; Eyebrows; Facial animation; Muscles; Shape; facial action coding system; facial expression; parameterization; radial basis function;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Science & Education (ICCSE), 2014 9th International Conference on
  • Conference_Location
    Vancouver, BC
  • Print_ISBN
    978-1-4799-2949-8
  • Type

    conf

  • DOI
    10.1109/ICCSE.2014.6926482
  • Filename
    6926482