Modeling hair from multiple views

ABSTRACT

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.

REFERENCES

• 1: Florence Bertails , Clément Ménier , Marie-Paule Cani, A practical self-shadowing algorithm for interactive hair animation, Proceedings of the 2005 conference on Graphics interface, May 09-11, 2005, Victoria, British Columbia
• 2: Johnny T. Chang , Jingyi Jin , Yizhou Yu, A practical model for hair mutual interactions, Proceedings of the 2002 ACM SIGGRAPH/Eurographics symposium on Computer animation, July 21-22, 2002, San Antonio, Texas [doi>10.1145/545261.545273]
• 3: Olivier Faugeras , Quang-Tuan Luong , T. Papadopoulou, The Geometry of Multiple Images: The Laws That Govern The Formation of Images of A Scene and Some of Their Applications, MIT Press, Cambridge, MA, 2001
• 4: Olivier Faugeras, Three-dimensional computer vision: a geometric viewpoint, MIT Press, Cambridge, MA, 1993
• 5: Allen Van Gelder , Jane Wilhelms, An interactive fur modeling technique, Proceedings of the conference on Graphics interface '97, p.181-188, May 1997, Kelowna, British Columbia, Canada
• 6: Grabli, S., Sillion, F., Marschner, S., and Lengyel, J. E. 2002. Image-based hair capture by inverse lighting. In Proc. Graphics Interface, pages 51--58.
• 7: Richard Hartley , Andrew Zisserman, Multiple view geometry in computer visiond, Cambridge University Press, New York, NY, 2001
• 8: Tae-Yong Kim , Ulrich Neumann, Interactive multiresolution hair modeling and editing, ACM Transactions on Graphics (TOG), v.21 n.3, July 2002
• 9: Kutulakos, K., and Seitz, S. 1999. A theory of shape by space carving. In IEEE ICCV, pages 307--314.
• 10: A. Laurentini, The Visual Hull Concept for Silhouette-Based Image Understanding, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.16 n.2, p.150-162, February 1994 [doi>10.1109/34.273735]
• 11: Maxime Lhuillier , Long Quan, A Quasi-Dense Approach to Surface Reconstruction from Uncalibrated Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.27 n.3, p.418-433, March 2005 [doi>10.1109/TPAMI.2005.44]
• 12: Stephen R. Marschner , Henrik Wann Jensen , Mike Cammarano , Steve Worley , Pat Hanrahan, Light scattering from human hair fibers, ACM Transactions on Graphics (TOG), v.22 n.3, July 2003
• 13: Wojciech Matusik , Chris Buehler , Ramesh Raskar , Steven J. Gortler , Leonard McMillan, Image-based visual hulls, Proceedings of the 27th annual conference on Computer graphics and interactive techniques, p.369-374, July 2000 [doi>10.1145/344779.344951]
• 14: Nakajima, M., Ming, K., and H. Takashi. 1998. Generation of 3d hair model from multiple pictures. IEEE Computer Graphics and Application vol 12, pages 169--183.
• 15: Paris, S., Briceno, H. M., and Sillion, F. X. 2004. Capture of hair geometry from multiple images. In Proc. of SIGGRAPH conference, ACM, pages 712--719.
• 16: Long Quan , Takeo Kanade, Affine Structure from Line Correspondences With Uncalibrated Affine Cameras, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.19 n.8, p.834-845, August 1997 [doi>10.1109/34.608285]
• 17: Richard Szeliski, Rapid octree construction from image sequences, CVGIP: Image Understanding, v.58 n.1, p.23-32, July 1993 [doi>10.1006/ciun.1993.1029]
• 18: Kelly Ward , Ming C. Lin, Adaptive Grouping and Subdivision for Simulating Hair Dynamics, Proceedings of the 11th Pacific Conference on Computer Graphics and Applications, p.234, October 08-10, 2003

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.5 Computational Geometry and Object Modeling
          Subjects: Modeling packages

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.5 Reconstruction

Keywords:
3D photography, hair modeling