DeepSketchHair: Deep Sketch-Based 3D Hair Modeling

• Published in: IEEE transactions on visualization and computer graphics 2021-07, Vol.27 (7), p.3250-3263
• Main Authors: Shen, Yuefan, Zhang, Changgeng, Fu, Hongbo, Zhou, Kun, Zheng, Youyi
• Format: Article
• Language: English
• Subjects: 3D volumetric structure; Computational modeling; Deep learning; Fields (mathematics); generative adversarial networks; Hair; Hairstyles; Model matching; Modelling; Neural networks; Sketch-based hair modeling; Sketches; Solid modeling; Three dimensional models; Three-dimensional displays; Two dimensional displays; Two dimensional models
• ISSN: 1077-2626; 1941-0506
• DOI: 10.1109/TVCG.2020.2968433

We present DeepSketchHair , a deep learning based tool for modeling of 3D hair from 2D sketches. Given a 3D bust model as reference, our sketching system takes as input a user-drawn sketch (consisting of hair contour and a few strokes indicating the hair growing direction within a hair region), and automatically generates a 3D hair model, matching the input sketch. The key enablers of our system are three carefully designed neural networks, namely, S2ONet , which converts an input sketch to a dense 2D hair orientation field; O2VNet , which maps the 2D orientation field to a 3D vector field; and V2VNet , which updates the 3D vector field with respect to the new sketches, enabling hair editing with additional sketches in new views. All the three networks are trained with synthetic data generated from a 3D hairstyle database. We demonstrate the effectiveness and expressiveness of our tool using a variety of hairstyles and also compare our method with prior art.