Image‐based authoring of herd animations

Abstract

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.

Authoring consistent landscapes with flora and fauna

“…The works [Wang et al 2014;Xu et al 2008] allow the user to control the shape taken by a group of animals. At the same time, Ecormier-Nocca et al [2019] extended control to both the shape and distribution of animals within a herd. However, while these approaches produce visually plausible animations, they do not consider the relationship ACM Trans.…”

“…that this simple implementation, sufficient for 3D illustration in this paper's context, does not take species-specific herd shapes into account [Ecormier-Nocca et al 2019], leaving space for improvement. Fig.…”

Authoring consistent landscapes with flora and fauna

“…that this simple implementation, sufficient for 3D illustration in this paper's context, does not take species-specific herd shapes into account [Ecormier-Nocca et al 2019], leaving space for improvement. We computed all maps using Python on a desktop with an Intel Xeon E5 processor and 32GB of RAM.…”