Molding Face Shapes by Example

  • Ira Kemelmacher
  • Ronen Basri
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)


Human faces are remarkably similar in global properties, including size, aspect ratios, and locations of main features, but can vary considerably in details across individuals, gender, race, or due to facial expression. We propose a novel method for 3D shape recovery of a face from a single image using a single 3D reference model of a different person’s face. The method uses the input image as a guide to mold the reference model to reach a desired reconstruction. Assuming Lambertian reflectance and rough alignment of the input image and reference model, we seek shape, albedo, and lighting that best fit the image while preserving the rough structure of the model. We demonstrate our method by providing accurate reconstructions of novel faces overcoming significant differences in shape due to gender, race, and facial expressions.


Facial Expression Input Image Reference Model Regularization Term Face Database 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Horn, B.: Obtaining Shape from Shading Information. The Psychology of Computer Vision. McGraw-Hill, New York (1975)Google Scholar
  2. 2.
    Horn, B., Brooks, M. (eds.): Shape from Shading. MIT Press, Cambridge (1989)Google Scholar
  3. 3.
    Rouy, E., Tourin, A.: A viscosity solutions approach to shape-from-shading. SIAM Journal of Numerical Analysis 29(3), 867–884 (1992)MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Zhang, R., Tsai, P., Cryer, J., Shah, M.: Shape from shading: A survey. PAMI 21(8), 690–706 (1999)CrossRefMATHGoogle Scholar
  5. 5.
    Pentland, A.: Finding the illuminant direction. Journal Optical Society of America, 448–455 (1982)Google Scholar
  6. 6.
    Zheng, Q., Chellappa, R.: Estimation of illuminant direction, albedo, and shape from shading. PAMI 13(7), 680–702 (1991)CrossRefGoogle Scholar
  7. 7.
    Tsai, P., Shah, M.: Shape from shading with variable albedo. Optical Engineering, 121–1220 (1998)Google Scholar
  8. 8.
    Moses, Y., Edelman, S., Ullman, S.: Generalization to novel images in upright and inverted faces. Perception 25, 443–461 (1996)CrossRefGoogle Scholar
  9. 9.
    Shimshoni, I., Moses, Y., Lindenbaum, M.: Shape re-construction of 3d bilaterally symmetric surfaces. IJCV 39(2), 97–100 (2000)CrossRefMATHGoogle Scholar
  10. 10.
    Zhao, W., Chellappa, R.: Symmetric shape-from-shading using self-ratio image. IJCV 45, 55–75 (2001)CrossRefMATHGoogle Scholar
  11. 11.
    Atick, J., Griffin, P., Redlich, A.: Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images. Neural Computation 8(6), 1321–1340 (1996)CrossRefGoogle Scholar
  12. 12.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. SIGGRAPH I, 187–194 (1999)Google Scholar
  13. 13.
    Zhou, S.K., Chellappa, R., Jacobs, D.W.: Characterization of human faces under illumination variations using rank, integrability, and symmetry constraints. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 588–601. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  14. 14.
    Smith, W., Hancock, E.: Recovering facial shape and albedo using a statistical model of surface normal direction. ICCV, 588–595 (2005)Google Scholar
  15. 15.
    Romdhani, S., Vetter, T.: Efficient, robust and accurate fitting of a 3d morphable model. ICCV (2003)Google Scholar
  16. 16.
    Dovgard, R., Basri, R.: Statistical symmetric shape from shading for 3D structure recovery of faces. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 99–113. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  17. 17.
    Sim, T., Kanade, T.: Combining models and exemplars for face recognition: An illuminating example. In: CVPR Workshop on Models versus Exemplars (2001)Google Scholar
  18. 18.
    Zhang, L., Samaras, D.: Face recognition under variable lighting using harmonic image exemplars. In: CVPR, vol. I, pp. 19–25 (2003)Google Scholar
  19. 19.
    Shashua, A., Riklin-Raviv, T.: The quotient image: Class based re-rendering and recognition with varying illuminations. PAMI 23(2), 129–139 (2001)CrossRefGoogle Scholar
  20. 20.
    Basri, R., Jacobs, D.: Lambertian reflectance and linear subspaces. PAMI 25(2), 218–233 (2003)CrossRefGoogle Scholar
  21. 21.
    Ramamoorthi, R., Hanrahan, P.: On the relationship between radiance and irradiance: Determining the illumination from images of a convex lambertian object. JOSA 18(10), 2448–2459 (2001)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Frolova, D., Simakov, D., Basri, R.: Accuracy of spherical harmonic approximations for images of lambertian objects under far and near lighting. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 574–587. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  23. 23.
    Dupuis, P., Oliensis, J.: An optimal control formulation and related numerical methods for a problem in shape reconstruction. The Annals of Applied Probability 4(2), 287–346 (1994)MathSciNetCrossRefMATHGoogle Scholar
  24. 24.
    Kimmel, R., Sethian, J.: Optimal algorithm for shape from shading and path planning. Journal of Mathematical Imaging and Vision 14(3), 237–244 (2001)MathSciNetCrossRefMATHGoogle Scholar
  25. 25.
    Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: generative models for recognition under variable pose and illumination. PAMI 23(6), 643–660 (2001)CrossRefGoogle Scholar
  26. 26.
    USF DARPA Human-ID 3D Face Database: Courtesy of Prof. Sudeep Sarkar, University of South Florida, Tampa, FL,

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ira Kemelmacher
    • 1
  • Ronen Basri
    • 1
  1. 1.Dept. of Computer Science and Applied Math.The Weizmann Institute of ScienceRehovotIsrael

Personalised recommendations