A Comparison of Two Machine Learning Approaches for Photometric Solids Compression

  • Samuel Delepoulle
  • François Rousselle
  • Christophe Renaud
  • Philippe Preux
Part of the Studies in Computational Intelligence book series (SCI, volume 321)

Abstract

The use of photometric solids into both real time and photorealistic rendering allows designers and computer artists to enhance easily the quality of their images. Lots of such data are available from lighting societies since they allow these societies to easily present the luminance distribution of their often complex ligthing systems. When accuracy is required the amount of discretized luminance directions and the number of photometric solids that have to be used increase considerably the memory requirements and reduce the algorithm efficiency. In this paper we describe and compare two machine learning approaches used for approximating any photometric solid: an artificial neural network and ECON (Equi-Correlated Network Algorithm). By applying these two approaches on a large set of real photometric distribution data, we were able to show that one of them provides generally a better approximation of the original distribution.

Keywords

approximation image render machine learning photometric solids light distribution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [CPB06]
    Claustres, L., Paulin, M., Boucher, Y.: A Wavelet-Based Framework for Acquired Radiometric Quantity Representation and Accurate Physical Rendering. The Visual Computer 22(4), 221–237 (2006)CrossRefGoogle Scholar
  2. [Den02]
    Deniel, J.M.: Modélisation des luminaires et des BRDF: réalisation, mesure et compression. PhD thesis, Université de Rennes 1 (2002)Google Scholar
  3. [DRP09]
    Delepoulle, S., Renaud, C., Preux, P.: Light source storage and interpolation for global illumination: a neural solution. In: Plemenos, D., Miaoulis, G. (eds.) Artificial Intelligence Techniques for Computer Graphics. Studies in Computational Intelligence, vol. 159, pp. 87–104. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  4. [EHJT04]
    Efron, B., Hastie, T., Johnstone, I.M., Tibshirani, R.: Least angle regression. Annals of Statistics 32(2), 407–499 (2004)MATHCrossRefMathSciNetGoogle Scholar
  5. [Hay08]
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 3rd edn. Prentice Hall, Englewood Cliffs (2008)Google Scholar
  6. [IES95]
    IESNA. IESNA Standard File Format for Electronic Transfer of Photometric Data. Illuminating Engineering Society of North America, lm-63-1995 edn. (1995)Google Scholar
  7. [Led]
    Ledalite. Electronic online photometric data files library, http://www.ledalite.com/
  8. [LPDR09]
    Loth, L., Preux, P., Delepoulle, S., Renaud, C.: ECON: a Kernel Basis Pursuit Algorithm with Automatic Feature Parameter Tuning, and its Application to Photometric Solids Approximation. In: Wani, M.A., Kantardzic, M., Palade, V., Kurgan, L., Qi, Y. (eds.) Proc. International Conference on Machine Learning and Applications (ICML-A), Miami, USA, pp. 162–169. IEEE Press, Los Alamitos (2009)CrossRefGoogle Scholar
  9. [Met]
    Metalumen. Electronic online photometric data files library, http://www.metalumen.com
  10. [NP00]
    Noé, N., Péroche, B.: Hierarchical reconstruction of brdfs using locally supported functions. Computer Graphics Forum 19(2), 173–183 (2000)MATHCrossRefGoogle Scholar
  11. [OPT00]
    Osborne, M.R., Presnell, B., Turlach, B.A.: A new approach to variable selection in least squares problems. IMA Journal of Numerical Analysis 20(3), 389–403 (2000)MATHCrossRefMathSciNetGoogle Scholar
  12. [R D09]
    R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2009) ISBN 3-900051-07-0Google Scholar
  13. [SAWG91]
    Sillion, F., Arvo, J., Westin, S., Greenberg, D.: A global illumination solution for general reflectance distributions. Computers Graphics 25(4), 187–196 (1991)CrossRefGoogle Scholar
  14. [WSC06]
    Walder, C., Schölkopf, B., Chapelle, O.: Implicit surface modelling with a globally regularised basis of compact support. Computer Graphics Forum 25(3), 635–644 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Samuel Delepoulle
    • 1
  • François Rousselle
    • 1
  • Christophe Renaud
    • 1
  • Philippe Preux
    • 2
  1. 1.Université Lille- Nord de France ULCO LISICCalais cedex
  2. 2.Centre de Recherche INRIA-Lille Nord Europe & Laboratoire d’Informatique, Fondamentale de Lille (LIFL, UMR CNRS 8022)Université de LilleVilleneuve d’Ascq

Personalised recommendations