Advertisement

Face Image Relighting using Locally Constrained Global Optimization

  • Jiansheng Chen
  • Guangda Su
  • Jinping He
  • Shenglan Ben
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6314)

Abstract

A face image relighting method using locally constrained global optimization is presented in this paper. Based on the empirical fact that common radiance environments are locally homogeneous, we propose to use an optimization based solution in which local linear adjustments are performed on overlapping windows throughout the input image. As such, local textures and global smoothness of the input image can be preserved simultaneously when applying the illumination transformation. Experimental results demonstrate the effectiveness of the proposed method comparing to some previous approaches.

Keywords

Face Image Target Face Ratio Image Local Window Active Appearance Model 
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.

References

  1. 1.
    Debevec, P., Hawkins, T., Tchou, C., Duiker, H.P., Sarokin, W., Sagar, M.: Acquiring the Reflectance Field of a Human Face. In: Proceeding of ACM SIGGRAPH, pp. 145–156 (2000)Google Scholar
  2. 2.
    Marschner, S.R., Greenberg, D.P.: Inverse Lighting for Photography. In: Proceedings of Fifth Color Imaging Conference, pp. 262–265 (1997)Google Scholar
  3. 3.
    Shashua, A., Raviv, T.R.: The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations. IEEE Trans. on PAMI 23(2), 129–139 (2001)Google Scholar
  4. 4.
    Ramamoorthi, R., Hanrahan, P.: An efficient representation for irradiance environment maps. In: Proceedings of ACM SIGGRAPH, pp. 497–500 (2001)Google Scholar
  5. 5.
    Basri, R., Jacobs, D.W.: Lambertian Reflectance and Linear Subspaces. IEEE Trans. on PAMI 25(2), 218–233 (2003)Google Scholar
  6. 6.
    Zhang, L., Wang, S., Samaras, D.: Face synthesis and recognition from a single image under arbitrary unkown lighting using a spherical harmonic basis morphable model. In: Proceedings of IEEE CVPR, pp. 209–216 (2005)Google Scholar
  7. 7.
    Wang, Y., Liu, Z., Hua, G., Wen, Z., Zhang, Z., Samaras, D.: Face Re-Lighting from a Single Image Under Harsh Lighting Conditions. In: Proceedings of IEEE CVPR (2007)Google Scholar
  8. 8.
    Peers, P., Tamura, N., Matusik, M., Debevec, P.: Post-production Facial Performance Relighting using Reflectance Transfer. In: Proceedings of ACM SIGGRAPH (2007)Google Scholar
  9. 9.
    Marschner, S.R., Guenter, B., Raghupathy, S.: Modeling and Rendering for RealisticFacial Animation. In: Proceedings of Eurographics Rendering Workshop, pp. 231–242 (2000)Google Scholar
  10. 10.
    Stoschek, A.: Image-based re-rendering of faces for continuous pose and illumination directions. In: Proceedings of IEEE CVPR, pp. 582–587 (2000)Google Scholar
  11. 11.
    Liu, Z., Shan, Y., Zhang, Z.: Expressive expression mapping with ratio images. In: Proceedings of ACM SIGGRAPH, pp. 271–276 (2001)Google Scholar
  12. 12.
    Wen, Z., Liu, Z., Huang, T.: Face relighting with radiance environment maps. In: Proceedings of IEEE CVPR, pp. 157–165 (2003)Google Scholar
  13. 13.
    Ramamoorthi, R., Hanrahan, P.: On the Relationship between Radiance and Irradiance: Determining the Illumination from Images of Convex Lambertian Object. J. Optical Soc. Am. 18(10), 2448–2459 (2001)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Ramamoorthi, R., Hanrahan, P.: An efficient representation for irradiance environment maps. In: Proceedings of ACM SIGGRAPH, pp. 497–500 (2001)Google Scholar
  15. 15.
    Lee, K.C., Ho, J., Kriegman, D.: Nine Points of Light: Acquiring Subspaces for Face Recognition under Variable Lighting. In: Proceedings of IEEE CVPR, pp. 357–362 (2001)Google Scholar
  16. 16.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active Appearance Models. IEEE Trans on PAMI 23(6), 681–685 (2001)Google Scholar
  17. 17.
    Matthews, I., Baker, S.: Active Appearance Models Revisited. Int’l J. Computer Vision 60(2), 135–164 (2004)CrossRefGoogle Scholar
  18. 18.
    Donner, R., Reiter, M., Langs, G., Peloschek, P., Bischof, H.: Fast Active Appearance Model Search Using Canonical Correlation Analysis. IEEE Trans. on PAMI 28(10), 1690–1694 (2006)Google Scholar
  19. 19.
    Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. on PAMI 23(6), 643–660 (2001)Google Scholar
  20. 20.
    Gao, W., Cao, B., Shan, S., Chen, X., Zhou, D., Zhang, X., Zhao, D.: The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations. IEEE Trans. on SMC, Part A 38(1) (2008)Google Scholar
  21. 21.
    Bookstein, F.L.: Principal Warps: Thin-Plate Splines and the Decomposition of Deformations. IEEE Trans. on PAMI 11(6) (1989)Google Scholar
  22. 22.
    Levin, A., Lischinski, D., Weiss, Y.: A Closed Form Solution to Natural Image Matting. IEEE Trans. on PAMI 30(2), 1–15 (2008)Google Scholar
  23. 23.
    Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)zbMATHGoogle Scholar
  24. 24.
    Schenk, O., Gärtner, K.: Solving Unsymmetric Sparse Systems of Linear Equations with PARDISO. J. of Future Generation Computer Systems 20(3), 475–487 (2004)CrossRefGoogle Scholar
  25. 25.
    Schenk, O., Gärtner, K.: On fast factorization pivoting methods for symmetric indefinite systems. Elec. Trans. Numer. Anal. 23, 158–179 (2006)zbMATHGoogle Scholar
  26. 26.
    Schenk, O., Bollhoefer, M., Roemer, R.: On large-scale diagonalization techniques for the Anderson model of localization. SIAM Review 50, 91–112 (2008)zbMATHCrossRefMathSciNetGoogle Scholar
  27. 27.
    Schenk, O., Waechter, A., Hagemann, M.: Matching-based Preprocessing Algorithms to the Solution of Saddle-Point Problems in Large-Scale Nonconvex Interior-Point Optimization. J. of Comput. Opt. and App. 36(2-3), 321–341 (2007)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jiansheng Chen
    • 1
  • Guangda Su
    • 1
  • Jinping He
    • 1
  • Shenglan Ben
    • 1
  1. 1.Department of Electronic EngineeringTsinghua UniversityP.R. China

Personalised recommendations