Realistic hair modeling from a hybrid orientation field

Image-based hair modeling methods enable artists to produce abundant 3D hair models. However, the reconstructed hair models could not preserve the structural details, such as uniformly distributed hair roots, interior strands growing in line with real distribution and exterior strands similar to images. In this paper, we propose a novel approach to construct a realistic 3D hair model from a hybrid orientation field. Our hybrid orientation field is generated from four fields. The first field makes the surface structure of a hairstyle be similar to the input images as much as possible. The second field makes the hair roots and interior hair strands be consistent with actual distribution. The tracing hair strands can be confined to the hair volume according to the third field. And the fourth field makes the growing direction of one point at a strand be compatible with its predecessor. To generate these fields, we construct high-confidence 3D strand segments from the orientation field of point cloud and 2D traced strands. Hair strands automatically grow from uniformly distributed hair roots according to the hybrid orientation field. We use energy minimization strategy to optimize the entire 3D hair model. We demonstrate that our approach can preserve structural details of 3D hair models.

[1]  Steve Marschner,et al.  A Survey on Hair Modeling: Styling, Simulation, and Rendering , 2007, IEEE Transactions on Visualization and Computer Graphics.

[2]  Chongyang Ma,et al.  Single-view hair modeling using a hairstyle database , 2015, ACM Trans. Graph..

[3]  Yue Qi,et al.  Dynamic hair capture using spacetime optimization , 2014, ACM Trans. Graph..

[4]  Hui Chen,et al.  A literature survey on smart cities , 2015, Science China Information Sciences.

[5]  Szymon Rusinkiewicz,et al.  Structure-aware hair capture , 2013, ACM Trans. Graph..

[6]  Cem Yuksel,et al.  Dual scattering approximation for fast multiple scattering in hair , 2008, ACM Trans. Graph..

[7]  Weijie Wang,et al.  Real-time camera tracking using hybrid features in mobile augmented reality , 2015, Science China Information Sciences.

[8]  Frédo Durand,et al.  Hair photobooth , 2008, SIGGRAPH 2008.

[9]  Simon R. Arridge,et al.  Diffusion tensor magnetic resonance image regularization , 2004, Medical Image Anal..

[10]  Paul A. Beardsley,et al.  Coupled 3D reconstruction of sparse facial hair and skin , 2012, ACM Trans. Graph..

[11]  Long Quan,et al.  Sketching hairstyles , 2007, SBIM '07.

[12]  Bernard Chazelle,et al.  Shape distributions , 2002, TOGS.

[13]  Frédo Durand,et al.  Single Photo Estimation of Hair Appearance , 2009 .

[14]  Kun Zhou,et al.  Dynamic hair manipulation in images and videos , 2013, ACM Trans. Graph..

[15]  Erdem Yörük,et al.  Structure preserving regularization of DT-MRI vector fields by nonlinear anisotropic diffusion filtering , 2005, 2005 13th European Signal Processing Conference.

[16]  Bülent Özgüç,et al.  3D Hair sketching for real-time dynamic & key frame animations , 2008, The Visual Computer.

[17]  Chongyang Ma,et al.  Robust hair capture using simulated examples , 2014, ACM Trans. Graph..

[18]  Kun Zhou,et al.  Single-view hair modeling for portrait manipulation , 2012, ACM Trans. Graph..

[19]  David Levin,et al.  The approximation power of moving least-squares , 1998, Math. Comput..

[20]  Arno Zinke,et al.  Lighting hair from the inside , 2012, ACM Trans. Graph..

[21]  Kun Zhou,et al.  High-quality hair modeling from a single portrait photo , 2015, ACM Trans. Graph..

[22]  Andrew Selle,et al.  To appear in the ACM SIGGRAPH conference proceedings A Mass Spring Model for Hair Simulation , 2008 .

[23]  Eyal Ofek,et al.  Video-Based Modeling of Dynamic Hair , 2009, PSIVT.

[24]  Diego Gutierrez,et al.  Capturing and stylizing hair for 3D fabrication , 2014, ACM Trans. Graph..

[25]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Steve Marschner,et al.  Capturing hair assemblies fiber by fiber , 2009, SIGGRAPH 2009.

[27]  Szymon Rusinkiewicz,et al.  Wide-Baseline Hair Capture Using Strand-Based Refinement , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Long Quan,et al.  Modeling hair from multiple views , 2005, SIGGRAPH 2005.

[29]  Marie-Paule Cani,et al.  Super-helices for predicting the dynamics of natural hair , 2006, ACM Trans. Graph..

[30]  Kun Zhou,et al.  Example-based hair geometry synthesis , 2009, ACM Trans. Graph..

[31]  P. Hanrahan,et al.  Light Scattering from Human Hair Fibers , 2003 .

[32]  Zhan Yu,et al.  A hybrid image-CAD based system for modeling realistic hairstyles , 2014, I3D.

[33]  彰 柏木,et al.  “Physically-Accurate Fur Reflectance: Modeling, Measurement and Rendering”の実装報告 , 2016 .