Abstract
This paper presents a neural network (NN) to recover three-dimensional (3D) shape of an object from its multiple view images. The object may contain non-overlapping transparent and opaque surfaces. The challenge is to simultaneously reconstruct the transparent and opaque surfaces given only a limited number of views. By minimizing the pixel error between the output images of this NN and teacher images, we want to refine vertices position of an initial 3D polyhedron model to approximate the true shape of the object. For that purpose, we incorporate a ray tracing formulation into our NN’s mapping and learning. At the implementation stage, we develop a practical regularization learning method using texture mapping instead of ray tracing. By choosing an appropriate regularization parameter and optimizing using hierarchical learning and annealing strategies, our NN gives more approximate shape.
This work is supported by The Japan Society for Promotion of Science.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Matusik, M., Hanspeter, P., Zieglar, R., Ngan, N., McMillan, L.: Acquisition and Rendering of Transparent and Refractive Objects, Rendering Techniques, 267–278 (2002)
Zongker, D.E., Werner, D.M., Curless, B., Salesin, D.: Environment Matting and Compositing. In: SIGGRAPH, pp. 205–214 (1999)
Bolle, R.M., Vemuri, B.C.: On three-dimensional surface reconstruction methods. IEEE Trans. on PAMI 13(1), 1–13 (1991)
Saito, M., Kashiwagi, H., Sato, Y., Ikeuchi, K.: Measurement of Surface Orientations of Transparent Objects Using Polarization in Highlight. In: CVPR, p. 1381- (1999)
Interrante, V., Fuchs, H., Pizer, S.M.: Conveying the 3D Shape of Smoothly Curving Transparent Surfaces via Texture. IEEE Trans. on VCG 3(2) (1997)
Murase, H.: Surface Shape Reconstruction of a Nonrigid Transport Object Using Refraction and Motion. IEEE Trans. on PAMI 14(10), 1045–1052 (1992)
Hata, S., Saitoh, Y., Kumamura, S., Kaida, K.: Shape Extraction of Transparent Object Using Genetic Algorithm. In: ICPR 1996, D93.6 (1996)
Wolff, L.B.: Shape from Polarization Images. In: CVWS 1997, pp. 79–85 (1987)
Fanany, M.I., Kobayashi, K., Kumazawa, I.: A combinatorial transparent surface modeling from polarization images. In: Klette, R., Žunić, J. (eds.) IWCIA 2004. LNCS, vol. 3322, pp. 65–76. Springer, Heidelberg (2004)
Miyazaki, D., Saito, M., Sato, Y., Ikeuchi, K.: Determining surface orientations of transparent objects based on polarization degrees in visible and infrared wavelengths. JOSA-A 19(4) (2002)
Miyazaki, D., Kagesawa, M., Ikeuchi, K.: Polarization-based Transparent Surface Modeling from Two Views. In: ICCV, pp. 1381–1386 (2003)
Rahman, S., Centerakis, N.: Reconstruction of Specular Surfaces using Polarization Imaging. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds.) EMMCVPR 2001. LNCS, vol. 2134, pp. 149–155. Springer, Heidelberg (2001)
Chuang, Y., Zongker, E., Hindorff, J., Curless, B., Salesin, D., Szeliski, R.: Environment matting extensions: towards higher accuracy. In: SIGGRAPH, pp. 121–130 (2000)
Wexler, Y., Fitzgibbon, A.W., Zisserman, A.: Image-based Environment matting. Rendering Techniques, 279–290 (2002)
Szeliski, R.: Avidan, Shai., Anandan, P.: Layer Extraction from Multiple Images Containing Reflections and Transparency. In: CVPR, p. 1246- (2000)
Fanany, M.I., Kumazawa, I.: Multiple-View Shape Extraction from Shading as Local Regression by Analytic NN Scheme. Mathematical and Computer Modelling 40(9-10), 959–975 (2004)
Fanany, M.I., Kumazawa, I.: A neural network for recovering 3D shape from erroneous and few depth maps of shaded images. Pattern Recognition Letters 25(4), 377–389 (2004)
Fanany, M.I., Ohno, M., Kumazawa, I.: A Scheme for Reconstructing Face from Shading using Smooth Projected Polygon NN. In: ICIP, vol. II, pp. 305–308 (2002)
Smith, A.R., Blinn, J.F.: Blue Screen Matting. In: SIGGRAPH, pp. 259-268 (1996)
Chen, Z., Haykin, S.: On Different Facets of Regularization Theory. Neural Computation 14(12), 2791–2846 (2002)
Hearn, D., Baker, M.P.: Computer Graphics: C Version. Prentice Hall, Upper Saddle River (1998)
Wolff, B., Kurlander, D.J.: Ray Tracing with Polarization Parameters, IEEE Computer Graphics Appl. 10(6), 44–55 (1990)
Romeo, F., Vincentelli, A.S.: A theoretical framework for Simulated Annealing. Algorithmica 6, 302–345 (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fanany, M.I., Kumazawa, I. (2006). A Neural Network for Simultaneously Reconstructing Transparent and Opaque Surfaces. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2006. Lecture Notes in Computer Science, vol 4142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11867661_15
Download citation
DOI: https://doi.org/10.1007/11867661_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44894-5
Online ISBN: 978-3-540-44896-9
eBook Packages: Computer ScienceComputer Science (R0)