Interactive control of avatars animated with human motion data

TLDR

Real‑time control of 3‑D avatars is crucial for games and virtual environments, yet it is challenging because users must choose from a large set of behaviors using low‑dimensional input devices. This work demonstrates that a large, unlabeled motion database can be preprocessed to enable flexible, efficient real‑time avatar control. We preprocess the motion data by identifying plausible transitions between segments, clustering them into a graph, and provide three interface techniques—selection, path sketching, and live motion capture—to navigate the graph. The approach is validated on four applications, showing that avatar motion closely matches directly recorded human motion.

Abstract

Real-time control of three-dimensional avatars is an important problem in the context of computer games and virtual environments. Avatar animation and control is difficult, however, because a large repertoire of avatar behaviors must be made available, and the user must be able to select from this set of behaviors, possibly with a low-dimensional input device. One appealing approach to obtaining a rich set of avatar behaviors is to collect an extended, unlabeled sequence of motion data appropriate to the application. In this paper, we show that such a motion database can be preprocessed for flexibility in behavior and efficient search and exploited for real-time avatar control. Flexibility is created by identifying plausible transitions between motion segments, and efficient search through the resulting graph structure is obtained through clustering. Three interface techniques are demonstrated for controlling avatar motion using this data structure: the user selects from a set of available choices, sketches a path through an environment, or acts out a desired motion in front of a video camera. We demonstrate the flexibility of the approach through four different applications and compare the avatar motion to directly recorded human motion.