Automatic Motion Generation Based on Path Editing from Motion Capture Data

In this paper, we present an integrated framework with easy and effective techniques to generate new motions of a character in real-time, using only a short segment of motion data. In this framework, a sequence of segment copies are strung together and then smoothed by a transition method at a junction of two consecutive segments. We use IK thought for the transition to solve the foot-slide problem at the junctions. Given a new motion path, we combine the IK constraints and the sequence of smoothed motion capture data to adjust the human-like model. Based on only a sample motion segment, our method can generate a sequence of motions following an arbitrary path specified by the user. Furthermore, it is easy to implement and can be applied to highly kinetic motions. The experimental results demonstrate our scheme.