Motion Parameterization with Inverse Blending

Motion blending is a popular motion synthesis technique which interpolates similar motion examples according to blending weighs parameterizing high-level characteristics of interest. We present in this paper an optimization framework for determining blending weights able to produce motions precisely satisfying multiple given spatial constraints. Our proposed method is simpler than previous approaches, and yet it can quickly achieve locally optimal solutions without pre–processing of basis functions. The effectiveness of our method is demonstrated in solving two classes of problems: 1) we show the precise control of end-effectors during the execution of diverse upper–body actions, and 2) we also address the problem of synthesizing walking animations with precise feet placements, demonstrating the ability to simultaneously meet multiple constraints and at different frames. Our several experimental results demonstrate that the proposed optimization approach is simple to implement and effectively achieves realistic results with precise motion control.