SA-Optimized Multiple View Smooth Polyhedron Representation NN

  • Mohamad Ivan Fanany
  • Itsuo Kumazawa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2843)


Simulated Annealing (SA) is a powerful stochastic search method that can produce very high quality solutions for hard combinatorial optimization problem. In this paper, we applied this SA method to optimize our 3D hierarchical reconstruction neural network (NN). This NN deals with complicated task to reconstruct a complete representation of a given object relying only on a limited number of views and erroneous depth maps of shaded images. The depth maps are obtained by Tsai-Shah shape-from-shading (SFS) algorithm. The experimental results show that the SA optimization enable our reconstruction system to escape from a local minima. Hence, it gives more exact and stable results with small additional computation time.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hartley, R., Zissermann, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  2. 2.
    Lehky, S.R., Sejnowski, T.J.: Network model of SFS: neural function arises from both receptive and projective fields. Nature 333, 452–454 (1988)CrossRefGoogle Scholar
  3. 3.
    Iwahori, Y., Woodham, R.J., Ozaki, M., Tanaka, H., Ishii, N.: Neural Network Based Photometric Stereo with a Nearby Rotational Moving Light Source. IEICE Trans. Inf & Syst. E80-D, 948–957 (1997)Google Scholar
  4. 4.
    Tsai, P.S., Shah, M.: Shape from Shading Using Linear Approximation. Image and Vision Computing Journal 12(8), 487–498 (1994)CrossRefGoogle Scholar
  5. 5.
    Wei, G.Q., Hirzinger, G.: Learning Shape from Shading by a Multilayer Network. IEEE Trans. On Neural Network 7(4), 985–995 (1996)CrossRefGoogle Scholar
  6. 6.
    Wei, G.Q., Hirzinger, G.: Parametric Shape-from-Shading by Radial Basis Functions. IEEE Trans. PAMI 19(4), 353–365 (1997)Google Scholar
  7. 7.
    Chowdhury, R., Chellappa, R., Krisnamurthy, S., Vo, T.: 3D Face Reconstruction from Video Using A Generic Model. In: Proceeding ICME (2002)Google Scholar
  8. 8.
    Faugeras, O., Luong, Q.T., Maybank, S.: Camera Self-calibration: theory and experiments. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 321–334. Springer, Heidelberg (1992)Google Scholar
  9. 9.
    Hartley, R.: In defence of the 8-point algorithm. In: Proc of the 5th Int. Conf. on Comp. Vision, pp. 1064–1070. IEEE Comp. Soc. Press, Boston (1995)CrossRefGoogle Scholar
  10. 10.
    Kumazawa, I., Ohno, M.: 3D Shape Reconstruction from Multiple Silhouettes: Generalization from Few Views by Neural Network Learning. In: Arcelli, C., Cordella, L.P., Sanniti di Baja, G. (eds.) IWVF 2001. LNCS, vol. 2059, pp. 687–695. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  11. 11.
    Romeo, F., Vincentelli, A.S.: A theoretical framework for Simulated Annealing. Algorithmica 6, 302–345 (1991)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Mohamad Ivan Fanany
    • 1
  • Itsuo Kumazawa
    • 1
  1. 1.Imaging Science and EngineeringTokyo Institute of Technology 

Personalised recommendations