Modeling hair from multiple views

In this paper, we propose a novel image-based approach to model hair geometry from images taken at multiple viewpoints. Unlike previous hair modeling techniques that require intensive user interactions or rely on special capturing setup under controlled illumination conditions, we use a handheld camera to capture hair images under uncontrolled illumination conditions. Our multi-view approach is natural and flexible for capturing. It also provides inherent strong and accurate geometric constraints to recover hair models.In our approach, the hair fibers are synthesized from local image orientations. Each synthesized fiber segment is validated and optimally triangulated from all visible views. The hair volume and the visibility of synthesized fibers can also be reliably estimated from multiple views. Flexibility of acquisition, little user interaction, and high quality results of recovered complex hair models are the key advantages of our method.

[1]  Ulrich Neumann,et al.  Interactive multiresolution hair modeling and editing , 2002, SIGGRAPH.

[2]  Long Quan,et al.  A quasi-dense approach to surface reconstruction from uncalibrated images , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Steve Marschner,et al.  Light scattering from human hair fibers , 2003, ACM Trans. Graph..

[4]  Jane Wilhelms,et al.  An Interactive Fur Modeling Technique , 1997, Graphics Interface.

[5]  Steve Marschner,et al.  Image-Based Hair Capture by Inverse Lighting , 2002, Graphics Interface.

[6]  Marie-Paule Cani,et al.  A practical self-shadowing algorithm for interactive hair animation , 2005, Graphics Interface.

[7]  A. Laurentini,et al.  The Visual Hull Concept for Silhouette-Based Image Understanding , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Sylvain Paris,et al.  Capture of hair geometry from multiple images , 2004, SIGGRAPH 2004.

[9]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[10]  Ramesh Raskar,et al.  Image-based visual hulls , 2000, SIGGRAPH.

[11]  Olivier D. Faugeras,et al.  The geometry of multiple images - the laws that govern the formation of multiple images of a scene and some of their applications , 2001 .

[12]  Kiriakos N. Kutulakos,et al.  A Theory of Shape by Space Carving , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[13]  Andrew Zisserman,et al.  Multiple view geometry in computer visiond , 2001 .

[14]  Yizhou Yu,et al.  A practical model for hair mutual interactions , 2002, SCA '02.

[15]  Richard Szeliski,et al.  Rapid octree construction from image sequences , 1993 .

[16]  Takeo Kanade,et al.  Affine structure from line correspondences with uncalibrated affine cameras , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Ming C. Lin,et al.  Adaptive grouping and subdivision for simulating hair dynamics , 2003, 11th Pacific Conference onComputer Graphics and Applications, 2003. Proceedings..