Animating Characters Using Nonparametric Regression

Abstract

In this paper, we propose an image deformation technique using nonparametric regression to animate characters in a still image for multimedia applications. The proposed approach effectively produces a sequence of contiguous frames in an animation. It automatically generates deformed shapes by using elliptic radial basis functions (ERBFs) and locally weighted regression (LOESS). ERBFs are used for representing the deformed character's shapes in synthesized frames. For preserving the pattern within a shape, LOESS is applied to fit the detail with local control. Furthermore, the results show the synthesized frames without unnatural distortion.