• 

Fully automatic hair modeling from a single image: Given a single portrait image as input, our method computes a hair segmentation and a hair growth direction map, which are used to obtain a matching hair shape from a large set of 3D model exemplars. A complete and high-quality 3D hair model is then generated based on the matching shape and the direction map. The whole process is fully automatic, with no user interaction or parameter tuning.

Abstruct

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.

Results

Resources