Image-based authoring of herd animations.

Animating herds of animals while achieving both convincing global shapes and plausible distributions within the herd is difficult, using simulation methods. In this work, we allow users to rely on photos of real herds, which are widely available, for keyframing their animation. More precisely, we learn global and local distribution features in each photo of the input set (which may depict different numbers of animals) and transfer them to the group of animals to be animated, thanks to a new statistical learning method enabling to analyze distributions of ellipses, as well as their density and orientation fields. The animated herd reconstructs the desired distribution at each keyframe while avoiding obstacles. As our results show, our method offers both high-level user control and help toward realism, enabling to easily author herd animations.