Improvement of pose imitation method: A signal processing perspective

Pose imitation is for two shapes to study pose from each other. It has been a hot area in shape deformation and we improve the original graphical pose imitation method by introducing signal thought. Laplace framework is often used in pose imitation and geometrical information involved Laplace operator performs better in preserving original shape's mass smooth part by carrying much intrinsic information of graph. However, the two shapes' bases in Laplace feature space need to be well mapped before utilizing classical pose imitation algorithm, which makes it an obstacle to introduce the geometry related Laplace operator. In our work, the problem is solved by proposing signal transfer algorithm and based on it, we put out an effective pose imitation framework using edge length related Laplace operator. Our method well suits to 2-dimension shape and good results of pose imitation have been achieved.