Published in ACM Transactions on Graphics, Volume 28, Issue 3 (SIGGRAPH 2009 Papers)

Example-Based Hair Geometry Synthesis


We present an example-based approach to hair modeling because creating hairstyles either manually or through image-based acquisition is a costly and time-consuming process. We introduce a hierarchical hair synthesis framework that views a hairstyle both as a 3D vector field and a 2D arrangement of hair strands on the scalp. Since hair forms wisps, a hierarchical hair clustering algorithm has been developed for detecting wisps in example hairstyles. The coarsest level of the output hairstyle is synthesized using traditional 2D texture synthesis techniques. Synthesizing finer levels of the hierarchy is based on cluster oriented detail transfer. Finally, we compute a discrete tangent vector field from the synthesized hair at every level of the hierarchy to remove undesired inconsistencies among hair trajectories. Improved hair trajectories can be extracted from the vector field. Based on our automatic hair synthesis method, we have also developed simple user-controlled synthesis and editing techniques including feature-preserving combing as well as detail transfer between different hairstyles.


Hair Modeling, Texture Synthesis, Hair Clustering, Detail Transfer, Vector Fields


basic hair synthesis results

Figure 1: Hair synthesis results from various examples. In each group, the input is on the left while the output is on the right. The inset shows the respective feature map.

hair detail transfer and combing results

Figure 2: Hair detail transfer (a, b, c) and combing (d) results. In the first three columns, the details from the hairstyles in the top row are transferred to the coarsest level of the hairstyles in the middle row to produce the final results in the bottom. In the rightmost column, three different hairstyles (as marked by dots in the first three columns) are edited using our detail-preserving comb.



We would like to thank Cem Yuksel, Sylvain Paris and colleagues for sharing their geometric hair data, Matt Scott for video dubbing, Steve Lin and Daisy Hao for help on writing, and the anonymous SIGGRAPH reviewers for their valuable suggestions.