Virtual cinematography of group scenes using hierarchical lines of actions

Abstract

We present an approach to generate shots for 3D computer graphics cinematic sequences from event-based descriptions of scenes of conversations between groups of actors. Our approach creates camera setups using a combination of geometric constraints and aesthetic parameters, while ensuring that the resulting cinematic sequence obeys the heuristics of good cinematography. More specifically, our main contributions are the a method for defining hierarchical lines of action and the identification and use of relevant first principles of cinematography for using these lines of actions. Our approach is more flexible and powerful than those proposed in previous work, mainly because it naturally generalizes to any number of actors in a scene.