Constructing Illumination Image Basis from Object Motion

  • Akiko Nakashima
  • Atsuto Maki
  • Kazuhiro Fukui
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


We propose to construct a 3D linear image basis which spans an image space of arbitrary illumination conditions, from images of a moving object observed under a static lighting condition. The key advance is to utilize the object motion which causes illumination variance on the object surface, rather than varying the lighting, and thereby simplifies the environment for acquiring the input images. Since we then need to re-align the pixels of the images so that the same view of the object can be seen, the correspondence between input images must be solved despite the illumination variance. In order to overcome the problem, we adapt the recently introduced geotensity constraint that accurately governs the relationship between four or more images of a moving object. Through experiments we demonstrate that equivalent 3D image basis is indeed computable and available for recognition or image rendering.


Reference Frame Input Image Principle Component Analysis Motion Parameter Object Motion 
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.


  1. 1.
    P.A. Beardsley, P. Torr, and A.P. Zisserman. 3D model acquisition from extended image sequences. In 4rd ECCV, pages 683–695, Cambridge, UK, 1996.Google Scholar
  2. 2.
    P.N. Belhumeur, J.P. Hespanha, and Kriegman D.J. Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE-PAMI, 19(7):711–720, 1997.Google Scholar
  3. 3.
    P.N. Belhumeur and D.J. Kriegman. What is the set of images of an object under all possible illumination conditions? IJCV, 28:3:245–260, 1998.CrossRefGoogle Scholar
  4. 4.
    R. Epstein, P.W. Hallinan, and A. Yuille. 5 +±2 Eigenimages suffice: an empirical investigation of low-dimensional lighting models. In Proc. IEEE Workshop on Physics-based Modeling in CV, 1995.Google Scholar
  5. 5.
    A.S. Georghiades, D.J. Kriegman, and P.N. Belhumeur. Illumination cones for recognition under variable lighting: Faces. In CVPR, pages 52–58, 1998.Google Scholar
  6. 6.
    P.W. Hallinan. A low-dimensional representation of human faces for arbitrary lighting conditions. In CVPR, pages 995–999, 1994.Google Scholar
  7. 7.
    R.I. Hartley. Euclidean reconstruction from uncalibrated views. In J.L. Mundy, A. Zisserman, and D. Forsyth, editors, Proc. Applications of Invariance in computer vision, pages 238–256. Springer-Verlag, 1994. Lecture Notes in Computer Science 825.Google Scholar
  8. 8.
    A. Maki, M. Watanabe, and C.S. Wiles. Geotensity: Combining motion and lighting for 3d surface reconstruction. In 6th ICCV, pages 1053–1060, 1998.Google Scholar
  9. 9.
    A. Maki and C. Wiles. Geotensity constraint for 3d surface reconstruction under multiple light sources. In 6th ECCV, pages 725–741, 2000.Google Scholar
  10. 10.
    Y. Moses, Y. Adini, and S. Ullman. Face recognition: the problem of compensating for changes in illumination direction. In J.O. Eckland, editor, 3rd ECCV, pages 286–296, Stockholm, Sweden, 1994. Springer-Verlag.Google Scholar
  11. 11.
    J.L. Mundy and A. Zisserman, editors. Geometric invariance in computer vision. The MIT Press, 1992.Google Scholar
  12. 12.
    H. Murase and S.K. Nayer. Visual learning and recognition of 3-d objects from appearance. IJCV, 14(1):5–24, 1995.CrossRefGoogle Scholar
  13. 13.
    A.P. Pentland. Photometric motion. IEEE-PAMI, 13:9:879–890, 1991.Google Scholar
  14. 14.
    A. Shashua. Geometry and photometry in 3D visual recognition. PhD thesis, Dept. Brain and Cognitive Science, MIT, 1992.Google Scholar
  15. 15.
    A. Shashua. On photometric issues in 3d visual recognition from a single 2d image. IJCV, 21:99–122, 1997.CrossRefGoogle Scholar
  16. 16.
    A. Shashua and T. Riklin-Raviv. The quotient image: Class-based re-rendering and recognition with varying illuminations. IEEE-PAMI, 23(2):129–139, 2001.Google Scholar
  17. 17.
    C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: a factorization method. IJCV, 9:2:137–154, 1992.CrossRefGoogle Scholar
  18. 18.
    D. Weinshall and C. Tomasi. Linear and incremental acquisition of invariant shape models from image sequences. In 4th ICCV, pages 675–682, 1993.Google Scholar
  19. 19.
    C.S. Wiles, A. Maki, and N. Matsuda. Hyper-patches for 3d model acquisition and tracking. IEEE-PAMI, 23(12):1391–1403, 2001.Google Scholar
  20. 20.
    R.J. Woodham. Photometric method for determining surface orientation from multiple images. Optical Engineering, 19:139–144, 1980.Google Scholar
  21. 21.
    A. Yuille and D. Snow. Shape and albedo from multiple images using integrability. In CVPR, pages 158–164, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Akiko Nakashima
    • 1
  • Atsuto Maki
    • 1
  • Kazuhiro Fukui
    • 1
  1. 1.Corporate Research and Development CenterTOSHIBA CorporationKawasakiJapan

Personalised recommendations