Facial Motion Capture Editing by Automated Orthogonal Blendshape Construction and Weight Propagation∗

We present a novel data-driven 3D facial motion capture data editing system by automated construction of an orthogonal blendshape face model and constrained weight propagation, aiming to bridge the popularized facial motion capture technique and blendshape approach. In this work, 3D facial motion capture editing problem is transformed to a blendshape animation editing problem. Given a collected facial motion capture dataset, we construct a truncated PCA space spanned by retained largest eigen-vectors 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. ∗This research has been funded by new faculty research start-up fund at University of Houston.