3D Surface Reconstruction of a Moving Object in the Presence of Specular Reflection

  • Atsuto Maki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)

Abstract

We present a new scheme for 3D surface reconstruction of a moving object in the presence of specular reflection. We basically search for the depth at each point on the surface of the object while exploiting the recently proposed geotensity constraint [7] that accurately governs the relationship between four or more images of a moving object in spite of the illumination variance due to object motion. The thrust of this paper is then to extend the availability of the geotensity constraint to the case that specularities are also present. The key idea is to utilise the fact that highlights shift on the surface due to object motion. I.e., we employ five or more images as inputs, and interchangeably utilise a certain intensity subset consisting of four projected intensities which is the least influenced by the specular component. We illustrate the relevancy of our simple algorithm also through experiments.

Keywords

Input Image Object Motion Depth Estimate Point Light Source Correct Depth 
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.
    Beardsley, P.A., Torr, P., Zisserman, A.: 3D model acquisition from extended image sequences. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 683–695. Springer, Heidelberg (1996)Google Scholar
  2. 2.
    Belhumeur, P.N., Kriegman, D.J.: What is the set of images of an object under all possible illumination conditions? IJCV 28(3), 245–260 (1998)CrossRefGoogle Scholar
  3. 3.
    Bhat, D.N., Nayar, S.: Stereo in the presence of specular reflection. In: 5th ICCV, pp. 1086–1092 (1995)Google Scholar
  4. 4.
    Devernay, F., Faugeras, O.: Computing di®erential properties of 3D shapes from stereoscopic images without 3d models. In: CVPR, pp. 208–213 (1994)Google Scholar
  5. 5.
    Fua, P.: Object-centered surface reconstruction: combining multi-image stereo and shading. IJCV 16, 35–56 (1995)CrossRefGoogle Scholar
  6. 6.
    Horn, B.K.P.: Robot Vision. The MIT Press, Cambridge (1992)Google Scholar
  7. 7.
    Maki, A., Watanabe, M., Wiles, C.S.: Geotensity: Combining motion and lighting for 3d surface reconstruction. IJCV 48(2), 75–90 (2002)MATHCrossRefGoogle Scholar
  8. 8.
    Nakashima, A., Maki, A., Fukui, K.: Constructing illumination image basis from object motion. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 195–209. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    Pentland, A.: Photometric motion. IEEE-PAMI 13(9), 879–890 (1991)Google Scholar
  10. 10.
    Shashua, A.: Geometry and photometry in 3D visual recognition. PhD thesis, Dept. Brain and Cognitive Science, MIT (1992)Google Scholar
  11. 11.
    Simakov, D., Srolova, D., Basri, R.: Dense shape reconstruction of a moving object under arbitrary, unknown lighting. In: 9th ICCV, pp. 1202–1209 (2003)Google Scholar
  12. 12.
    Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. IJCV 9(2), 137–154 (1992)CrossRefGoogle Scholar
  13. 13.
    Weber, M., Blake, A., Cipolla, R.: Towards a complete dense geometric and photometric reconstruction under varying pose and illumination. In: BMVC, pp. 83–92 (2002)Google Scholar
  14. 14.
    Wiles, C.S., Maki, A., Matsuda, N.: Hyper-patches for 3d model acquisition and tracking. IEEE-PAMI 23(12), 1391–1403 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Atsuto Maki
    • 1
  1. 1.Graduate School of InformaticsKyoto UniversityKyotoJapan

Personalised recommendations