Approximating Reflectance Functions using Neural Networks

  • David Gargan
  • Francis Neelamkavil
Conference paper
Part of the Eurographics book series (EUROGRAPH)


We present a new representation for the storage and reconstruction of arbitrary reflectance functions. This non-linear representation, based on a neural network model, accurately captures the spectral and spatial variation of these functions. It is both computationally efficient and concise, yet expressive. We reconstruct the subtle reflection characteristics of an analytic reflection model as well as measured and simulated reflection data


Activation Function Computer Graphic Hide Unit Reflectance Model Reflectance Function 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Blinn, James. “Models of Light Reflection for Computer Synthesised Pictures,” Computer Graphics, 11(4), July 1977Google Scholar
  2. 2.
    Cabral, Brian, Max Nelson and Springmeyer Rebecca. “Bi-directional Reflection Functions from Surface Bump Maps,” Computer Graphics, 21(4), July 1987Google Scholar
  3. 3.
    Cook, Robert L. and Torrence, Kenneth E., “A Reflectance Model for Computer Graphics,” Computer Graphics, 15(3), August 1981Google Scholar
  4. 4.
    Dana, K.J., Nayar S.K., vam Ginneken Bram and Kooenderink Jan J., “Reflectance and Texture of Real-World Surfaces”, Technical Report, Google Scholar
  5. 5.
    Glassner., Andrew, S., “Principles of Digital Images Synthesis,” The Morgan Kaufmann Series in Computer Graphics and Geometric Modelling. 1995Google Scholar
  6. 6.
    Gondek, Jay S., Meyer G.W., and Newmann J.G., “Wavelength Dependent Reflectance Functions” Computer Graphics, 28(4), July 1994Google Scholar
  7. 7.
    He, Xiao D., Torrence Kenneth E., Sillion, François X. and Greenberg Donald P., “A Comprehensive Physical Model for Light Reflection,” Computer Graphics, 25(4), July 1991Google Scholar
  8. 8.
    Kajiya, James T., “Anisotropic Reflectance Models,” Computer Graphics, 19(4), August 1985Google Scholar
  9. 9.
    Kajiya, James T., “The Rendering Equation,” Computer Graphics, 20(4), August 1986Google Scholar
  10. 10.
    Krueger, Wolfgang. “Intensity Fluctuations and Natural Texturing,” Computer Graphics, 22(4), August 1988Google Scholar
  11. 11.
    Kung., S.Y. Digital Neural Networks. Prentice Hall, 1992Google Scholar
  12. 12.
    LaFortune, Eric P. and Willems, Yves D., “Using the modified Phong Reflectance Model for Physically Based Rendering,” Report CW 197, Department of Computing Science, K.U. Leuven, November 1994.Google Scholar
  13. 13.
    LaFortune, Eric P., Foo, Sing-Choong, Torrence, Kenneth E. and Greenberg, Donald P., “Non-Linear Approximation of Reflectance Functions,” Computer Graphics, 31(4), August 1997.Google Scholar
  14. 14.
    Lalonde, Paul, “Representation and Uses of Light Distribution Functions,” PhD. Thesis, University of British Columbia, December 1997.Google Scholar
  15. 15.
    Lewis, Robert R., “Making Shaders More Physically Plausible,” In Proceedings of Fourth Eurographics Workshop on Rendering, Paris 1993Google Scholar
  16. 16.
    Meyer, G.W. “Wavelength Selection for Synthetic Image generation,” Computer Vision, Graphics and Image Processing. No 48, 1998Google Scholar
  17. 17.
    Neumann, L. “Photosimulation: interreflection with arbitrary reflectance models and illumination,” Computer Graphics Forum 8(1) March 1989Google Scholar
  18. 18.
    National Institute of Standards and Technology, United States Department of Commerce. Report of Workshop on Advanced Methods and Models for Appearance of Coatings and Coated Objects, March 1997Google Scholar
  19. 19.
    Oren, Michael and Nayar, Shreek., “Generalisation of Lambert’s Reflectance Model,” Computer Graphics, 22(4), August 1994, 28(4), July 1993Google Scholar
  20. 20.
    Phong, Bui-Tuong. “Illumination for Computer Generated Images.” Communications of the ACM, 18(6) 1975.Google Scholar
  21. 21.
    Poulin, Pierre and Fournier, Alain. “A Model for Anisotropic Reflection” Computer Graphics, 24(4), August 1990Google Scholar
  22. 22.
    Rosenblatt, F., “The perceptron: A probabilistic model for information storage and organisation in the brain,” Psychology Review Vol 65, 1958Google Scholar
  23. 23.
    Rummelhart, D. E., et. al. “Parallel Distributed Processing (PDP): Exploration in the Microstructure of Cognition,” volume 1. The MIT Press, Cambridge MA, 1986Google Scholar
  24. 24.
    Sanford, B. and Robertson D., “Infrared Reflectance Properties of aircraft Paints,” Proceedings of the 1985 Meeting of the IRIS Speciality Group on Targets, Backgrounds and Discrimination, February 1985Google Scholar
  25. 25.
    Schröder, Peter and Sweldens, Wim. “Spherical Wavelets: Efficiently Representing Functions on the Sphere,” Computer Graphics, 29(4), August 1995Google Scholar
  26. 26.
    Shirley, Peter, Wang, Changyaw and Zimmerman Kurt. “Monte Carlo Techniques for Direct Lighting Calculations,”Google Scholar
  27. 27.
    Strauss, P. S., “A realistic lighting model for computer animators,” IEEE Computer Graphics & Applications, 10(11) November 1990.Google Scholar
  28. 28.
    Ward, Gregory J., “Measuring and Modelling Anisotropic Reflection,” Computer Graphics, 26(2), July 1992Google Scholar
  29. 29.
    Westin, Stephen H., Arvo, James R. and Torrance Kenneth E., “Predicting Reflectance Functions from Complex Surfaces,” Computer Graphics, 26(2), July 1992Google Scholar

Copyright information

© Springer-Verlag Wien 1998

Authors and Affiliations

  • David Gargan
    • 1
  • Francis Neelamkavil
    • 1
  1. 1.Image Synthesis Group, Dept. of Computer ScienceTrinity College DublinIreland

Personalised recommendations