• DocumentCode
    3277927
  • Title

    Scene flow constrained multi-prior patch-sweeping for real-time upper body 3D reconstruction

  • Author

    Waizenegger, W. ; Feldmann, I. ; Schreer, O. ; Eisert, Peter

  • Author_Institution
    Heinrich Hertz Inst., Fraunhofer Inst. for Telecommun., Berlin, Germany
  • fYear
    2013
  • fDate
    15-18 Sept. 2013
  • Firstpage
    2086
  • Lastpage
    2090
  • Abstract
    We present a high performance real-time approach for robust 3D structure estimation of human bodies. Our idea extends state of the art high precision patch-sweep techniques by exploiting temporal information. By parameterizing 3D patches in the spatio-temporal domain we gain increased quality and robustness, while the computational complexity decreases drastically. The key to these improvements is the utilization of a global scene flow like prior called spatio-temporal object (STO). The target application of our method reaches from video communication and virtual eye contact scenarios till future digital cinema 3D post-production and real-time person modelling and modification. The result of this work extends a novel 3D scene representation developed in the EC research project SCENE.
  • Keywords
    computational complexity; image reconstruction; image representation; image sequences; rendering (computer graphics); video signal processing; 3D patch parameterization; 3D scene representation; EC research project; SCENE; STO; computational complexity; real-time upper body 3D reconstruction; realistic person rendering; robust 3D structure estimation; scene flow constrained multiprior patch-sweeping; spatio-temporal domain; spatio-temporal object; video communication scenarios; virtual eye contact scenarios; 3D reconstruction; real-time; scene flow; upper body;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing (ICIP), 2013 20th IEEE International Conference on
  • Conference_Location
    Melbourne, VIC
  • Type

    conf

  • DOI
    10.1109/ICIP.2013.6738430
  • Filename
    6738430