AutoHair: Fully Automatic

Hair Modeling from A Single Image


We introduce AutoHair, the first fully automatic method for 3D hair modeling from a single portrait image, with no user interaction or parameter tuning. Our method efficiently generates complete and high-quality hair geometries, which are comparable to those generated by the state-of-the-art methods, where user interaction is required. The core components of our method are: a novel hierarchical deep neural network for automatic hair segmentation and hair growth direction estimation, trained over an annotated hair image database; and an efficient and automatic data-driven hair matching and modeling algorithm, based on a large set of 3D hair exemplars. We demonstrate the efficacy and robustness of our method on Internet photos, resulting in a database of around 50K 3D hair models and a corresponding hairstyle space that covers a wide variety of real-world hairstyles. We also show novel applications enabled by our method, including 3D hairstyle space navigation and hair-aware image retrieval.



Data: The 3DHW database is available for research purpose upon request (email: kunzhou at acm dot org).


The authors would like to thank Liwen Hu and Hao Li for helping with the comparisons, the artists for making their hair models available on The Sims Resource and Newsea platform, the Flickr users for letting us use their work under the Creative Commons License, Yiying Tong for proofreading the paper, and the SIGGRAPH reviewers for their helpful comments. This work is partially supported by the NSF of China (No. 61272305, No. 61402402 and No. 61572429) and the National Program for Special Support of Eminent Professionals of China.