Abstract
This paper presents a novel neural network approach to recovering of 3D surfaces from single gray scale images. The proposed neural network uses photometric stereo to estimate local surfaces orientation for surfaces at each point of the surface that was observed from same viewpoint but with different illumination direction in surfaces that follow the Lambertian reflection model. The parameters for the neural network are a 3x3 brightness patch with pixel values of the image and the light source direction. The light source direction of the surface is calculated using two different approaches. The first approach uses a mathematical method and the second one a neural network method. The images used to test the neural network were both synthetic and real images. Only synthetic images were used to compare the approaches mainly because the surface was known and the error could be calculated. The results show that the proposed neural network is able to recover the surface with a highly accurately estimate.
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
Wei, G.Q., Hirzinger, G.: Learning shape from shading by a multilayer network. IEEE Transactions On Neural Networks 7, 985–994 (1996)
Mostafa, M.G.H., Yamany, S.M., Farag, A.A.: Integrating shape from shading and range data using neural networks. In: CVPR, pp. 2015–2020 (1999)
Ben-Arie, J., Nandy, D.: A neural network approach for reconstructing surface shape from shading. ICIP (2), 972–976 (1998)
Cheng, W.C.: Neural-network-based photometric stereo for 3d surface reconstruction. Neural Networks, 2006. In: IJCNN 2006. International Joint Conference, pp. 404–410 (2006)
Zhou, S.M., Li, H.X., Xu, L.D.: A variational approach to intensity approximation for remote sensing images using dynamic neural networks. Expert Systems 20, 163–170 (2003)
Grimson, W.: From Images to Surfaces: A Computational Study of the Human Early Visual System. MIT Press, Cambridge (1981)
Werbos, P.J.: Beyond Regression: NewTools for Prediction and Analysis in the Behavioral Sciences. PhD Thesis, Harvard University, Cambridge, MA, USA (1974)
Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation. In: Anderson, J., Rosenfeld, E. (eds.) Neurocomputing
Dan Foresee, F., Hagan, M.: Gauss-newton approximation to bayesian learning. In: International Conference on Neural Networks,1997, vol. 3, pp. 1930–1935 (1997)
MacKay, D.: Bayesian interpolation. Neural Computation 4(3), 415–447 (1992)
Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: Shape from shading: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 21(8), 690–706 (1999)
Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: A survey of shape from shading methods. Technical Report CS-TR-97-15, Computer Science Dept., Univ. of Central Florida (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Elizondo, D., Zhou, SM., Chrysostomou, C. (2008). Surface Reconstruction Techniques Using Neural Networks to Recover Noisy 3D Scenes. In: Kůrková, V., Neruda, R., KoutnÃk, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9_88
Download citation
DOI: https://doi.org/10.1007/978-3-540-87536-9_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87535-2
Online ISBN: 978-3-540-87536-9
eBook Packages: Computer ScienceComputer Science (R0)