SIGGRAPH Asia 2019 Neural State Machine for Character Scene Interactions

Animating characters is a difficult task when it comes to interacting with objects and the environment. What if we used computer brains instead In this research, we present the Neural State Machine, a datadriven deep learning framework that can handle such animations. The system is able to learn characterscene interactions from motion capture data, and produces highquality animations from simple control commands. The framework can be used for creating natural animations in games and films, and is the fi