Abstract
In this paper we present techniques for reusing view-dependent animation. First, we provide a framework for representing view-dependent animations. We formulate the concept of a view space - the space formed by the key views and their associated character poses. Tracing a path on the view space generates the corresponding view-dependent animation in real time. We then demonstrate that the framework can be used to synthesize new stylized animations by reusing view-dependent animations. We present three types of novel reuse techniques. In the first we show how to animate multiple characters from the same view space. Next, we show how to animate multiple characters from multiple view spaces. We use this technique to animate a crowd of characters. Finally, we draw inspiration from cubist paintings and create their view-dependent analogues, by using different cameras to control different body parts of the same character.