Abstract
Photorealistic lighting requires to use accurate rendering algorithms and realistic models of light sources. Photometric solids are provided by lighting designers in order to characterize the luminance distribution from real light sources. 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 algorithms efficiency. In this paper we propose to approximate any photometric solid by the way of artificial neural networks. The data describing the luminances distribution are used to train a dedicated neural network during a learning step. Then this much more compact representation of the data can be used both for reducing the memory requirements and the computation costs when searching for any luminance information.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Patrick, V.D., Ben Kröse, S.: An Introduction to Neural Network. The University of Amsterdam (1996)
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)
Coulom, R.: Feedforward neural networks in reinforcement learning applied to highdimensional motor control. In: 13th International Conference on Algorithmic Learning Theory, pp. 402–413. Springer, Heidelberg (2002)
Coulom, R.: Reinforcement Learning Using Neural Networks, with Applications to Motor Control. PhD thesis, Institut National Polytechnique de Grenoble (2002)
Cybenko, G.: Approximations by superpositions of sigmoidal functions. Math. Control, Signals, Systems 2, 303–314 (1989)
Deniel, J.M.: Modélisation des luminaires et des BRDF: réalisation, mesure et compression. PhD thesis, Université de Rennes 1 (2002)
Fahlman, S.E.: An empirical study of learning speed in back-propagation networks. Technical report (1988)
Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Advances in Neural Information Processing Systems 2, pp. 524–532. Morgan Kaufmann, San Francisco (1990)
Fontenla-Romero, O., Erdogmus, D., Príncipe, J.C., Alonso-Betanzos, A., Castillo, E.: Accelerating the convergence speed of neural networks learning methods using least squares. In: ESANN, pp. 255–260 (2003)
Sillion, X., Arvo, J., Westin, S., Greenberg, D.: A global illumination solution for general reflectance distributions. Computers Graphics 25(4), 187–196 (1991)
IESNA. IESNA Standard File Format for Electronic Transfer of Photometric Data. Illuminating Engineering Society of North America, lm-63-1995 edn. (1995)
McCulloch, W.S., Pitts, W.: A logical calculus of ideas immanent in neural activity. Bulletin of Mathematical Biophysics 5, 115–133 (1943)
Noé, N., Péroche, B.: Hierarchical reconstruction of brdfs using locally supported functions. Computer Graphics Forum 19(2), 173–183 (2000)
Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The rprop algorithm. In: Proceedings of the IEEE International Conference on Neural Networks, pp. 586–591 (1993)
Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge (1996)
Rosenblatt, F.: The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review 65, 386–408 (1958)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. pp. 318–362 (1986)
Schram, G., Karsten, L., Krose, B.J.A., Groen, F.C.A.: Optimal attitude control of satellites by artificial neural networks: a pilot study. In: Preprints of IFAC Symposium on Artificial Intelligence in Real-Time Control (AIRTC 1994), pp. 185–190 (1994)
Waugh, S., Adams, A.: A practical comparison between quickprop and backpropagation. In: The Eighth Australian Conference on Neural Networks, pp. 143–147 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Delepoulle, S., Renaud, C., Preux, P. (2009). Light Source Storage and Interpolation for Global Illumination: A Neural Solution. In: Plemenos, D., Miaoulis, G. (eds) Intelligent Computer Graphics 2009. Studies in Computational Intelligence, vol 240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03452-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-03452-7_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03451-0
Online ISBN: 978-3-642-03452-7
eBook Packages: EngineeringEngineering (R0)