Motion texture

TLDR

The authors introduce motion texture, a technique for synthesizing complex human‑figure motion that is statistically similar to captured dance data. Motion texture is defined as a set of motion textons modeled by linear dynamic systems and a transition matrix describing their distribution, and a maximum‑likelihood algorithm learns these from captured motion. The learned motion texture enables automatic generation and interactive editing of dance animations, can be manipulated at texton or distribution levels, and produces visually compelling synthesized sequences.

Abstract

In this paper, we describe a novel technique, called motion texture, for synthesizing complex human-figure motion (e.g., dancing) that is statistically similar to the original motion captured data. We define motion texture as a set of motion textons and their distribution, which characterize the stochastic and dynamic nature of the captured motion. Specifically, a motion texton is modeled by a linear dynamic system (LDS) while the texton distribution is represented by a transition matrix indicating how likely each texton is switched to another. We have designed a maximum likelihood algorithm to learn the motion textons and their relationship from the captured dance motion. The learnt motion texture can then be used to generate new animations automatically and/or edit animation sequences interactively. Most interestingly, motion texture can be manipulated at different levels, either by changing the fine details of a specific motion at the texton level or by designing a new choreography at the distribution level. Our approach is demonstrated by many synthesized sequences of visually compelling dance motion.