The Virtual Camera Composition (VCC) problem consists in auto- matically positioning a camera in a virtual world, such that the resulting image satisfies a set of visual cinematographic properties [3]. In this paper, we propose an approach to VCC based on Particle Swarm Optimization [5]. We show, in re- alistic situations, that our approach outperforms a discretized, exhaustive search method similar to a proposal by Bares et al [1].
