Collision detection in densely packed fiber assemblies with application to hair modeling

In this paper we investigate the application of bounding volume hierarchies in collision detection among densely, packed fiber assemblies like hair strands or cable looms. In particular, we glance at collision detection algorithms with sub-quadratic upper bound and their practicability and performance in complex dynamic hair scenes. Unlike common collision detection techniques our approach exploits the topological structure of the underlying filament assembly and allows for fast hierarchy, updates in dynamic deformable scenes. Furthermore, we compare hierarchies of the wrapped and the layered type and show the feasibility of fiber based collision detection on full human hair models. We simulate each fiber of an assembly, by, means of Cosserat rod models.