Our system takes a collection of images as input (a) and reconstructs a point cloud with a 3D orientation field (b). In contrast to previous methods (e.g. [Paris et al. 2008]) that straightforwardly grow hair strands from the scalp following the orientation field and hence cannot reconstruct complex hairstyles with convoluted curl structures (c), we reconstruct complete, coherent and plausible wisps (d) aware of the underlying hair structures. The wisps can be used to synthesize hair strands (e) that are plausible for animation or simulation (f).
Existing hair capture systems fail to produce strands that reflect the structures of real-world hairstyles. We introduce a system that reconstructs coherent and plausible wisps aware of the underlying hair structures from a set of still images without any special lighting. Our system first discovers locally coherent wisp structures in the reconstructed point cloud and the 3D orientation field, and then uses a novel graph data structure to reason about both the connectivity and directions of the local wisp structures in a global optimization. The wisps are then completed and used to synthesize hair strands which are robust against occlusion and missing data and plausible for animation and simulation. We show reconstruction results for a variety of complex hairstyles including curly, wispy, and messy hair.