Issue No.06 - November/December (2008 vol.28)
Qing Li , University of Houston
Zhigang Deng , University of Houston
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MCG.2008.120
The authors present a novel data-driven 3D facial motion capture data editing system using automated construction of an orthogonal blendshape face model and constrained weight propagation, aiming to bridge the popular facial motion capture technique and blendshape approach. In this work, a 3D facial-motion-capture-editing problem is transformed to a blendshape-animation-editing problem. Given a collected facial motion capture data set, we construct a truncated PCA space spanned by the greatest retained eigenvectors and a corresponding blendshape face model for each anatomical region of the human face. As such, modifying blendshape weights (PCA coefficients) is equivalent to editing their corresponding motion capture sequence. In addition, a constrained weight propagation technique allows animators to balance automation and flexible controls.
Motion editing, blendshape animation, facial animation, motion capture, data-driven, motion propagation
Qing Li, Zhigang Deng, "Orthogonal-Blendshape-Based Editing System for Facial Motion Capture Data", IEEE Computer Graphics and Applications, vol.28, no. 6, pp. 76-82, November/December 2008, doi:10.1109/MCG.2008.120