Motion transformation by example

Abstract

Animated characters bring the illusion of life to feature films, television shows, video games, and educational simulations. However, it is difficult for artists to define natural and expressive movement. This challenge is compounded by the fact that people are intrinsically sensitive to subtle inaccuracies in human motion. To address this problem, this thesis presents techniques that adjust existing character animations to meet new stylistic or temporal requirements. The proposed methods learn compact models of the appropriate transformations from examples provided by the user. By doing so, they are able to achieve compelling results without significant user effort or skill.