Abstract
Shape from shading is an important domain of computer vision and one of the approaches of 3D reconstruction. In this paper we propose a new method to reconstruct the surface of an object using neural networks. This approach ignores the details of the image for a big gain in noise resistance. It is based on the available boundary information of the surface of the shape to be reconstructed. We will use a neural network to evaluate the variation of the surface for a pixel based on the adjacent pixels. The small number of neurons ensures the speed of the algorithm. The approach is tested on synthetic and real images .
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 subscriptionsReferences
Daniel, P.: Peut-on extraire le relief d’une seule image ? Ph.D. thesis, IRIT, Université Paul Sabatier de Toulouse (2000)
Belhumeur, P.N., Kriegman, D.J., Yuille, A.L.: The bas-relief ambiguity. IJCV 35(1), 33–44 (1999)
Horn, B.K.P.: Shape From Shading: A Method for Obtaining the Shape of a Smooth Opaque Object From One View, Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA (1970)
Durou, J.-D., Falcone, M., Sagona, M.: Numerical methods for shape-from-shading: a new survey with benchmarks. Comput. Vis. Image Underst. 109(1), 22–43 (2008)
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)
Abada, L., Aouat, S.: Solving the perspective shape from shading problem using a new integration method. In: 2013 Science and Information Conference, pp. 416–422. IEEE (2013)
Ni, Q.J., Xing, H.C., Zhang, Z.Z., et al.: Survey of particle swarm optimization algorithm. Pattern Recogn. Artif. Intell. 20(3), 349–357 (2007)
Durou, J.D., Falcone, M., Sagona, M.: A survey of numerical methods shading. Technical report, IRIT, Université PaulSabatier, Toulouse (2004)
Horn, B.K.P.: Obtaining shape from shading information. In: Winston, P.H. (ed.) The Psychology of Computer Vision, McGraw-Hill, pp. 15–155 (1975). (Chapter 4)
Abada, L., Aouat, S.: Facial shape-from-shading using features detection method. Int. J. Adv. Intell. Paradigms 8(1), 3–19 (2016)
Abada, L., Aouat, S.: Enhanced variational approach by fast-marching to recover a 3D shape from shading. In: Proceedings of the 20th International Database Engineering and Applications Symposium, pp. 156–163 (2016)
Barles, G.: Solutions de viscosité des équations de Hamilton-Jacobi. Springer, Verlag (1994). (in French)
Rindfeisch, T.: Photometric method for lunar topography. Photom. Eng. 32(2), 262–277 (1966)
Rouy, E., Tourin, A.: A viscosity solutions approach to shape-from-shading. SIAM J. Numer. Anal. 29(3), 867–884 (1992)
Lions, P.-L., Rouy, E., Tourin, A.: Shape-from-shading, viscosity solutions and edges. Numerische Mathematik 64(3), 323–353 (1993)
J. Oliensis, P., Dupuis, A.: Global algorithm for shape from shading. In: Proceedings of the Fourth IEEE International Conference on Computer Vision, Berlin, Germany, pp. 692–701 (1993)
Ishii, H., Ramaswamy, M.: Uniqueness results for a class of Hamilton-Jacobi equations with singular coefficients. Commun. Partial Diff. Eqn. 20, 2187–2213 (1995)
Falcone, M., Sagona, M.: An algorithm for the global solution of the shape-from-shading model. In: Proceedings of the Ninth International Conference on Image Analysis and Processing (vol. I), Lecture Notes in Computer Science, Florence, Italy, vol. 1310, pp. 596–603 (1997)
Kain, J., Ostrov, D.N.: Numerical shape-from-shading for discontinuous photographic images. Int. J. Comput. Vis. 44(3), 163–173 (2001)
Prados, E., Faugeras, O.: A mathematical and algorithmic study of the Lambertian SFS problem for orthographic and pinhole cameras, Rapport de Recherche 5005, Institut National de Recherche en Informatique et en Automatique, Sophia Antipolis, France (2003)
Aabada, L., Aouat, S.: Tabu search to solve the shape from shading ambiguity. Int. J. Artif. Intell. Tools 24(05), 1550035 (2015)
Zheng, Q., Chellappa, R.: Estimation of illuminant direction, albedo, and shape from shading. IEEE Trans. Pattern Anal. Mach. Intell. 13(7), 680–702 (1991)
Pentland, A.: Shape information from shading: a theory about human perception. Proc. Int. Conf. Comput. Vis. 4, 404–413 (1988)
Abada, L., Aouat, S.: Shape from shading with and without boundary conditions. In: Intelligent Systems for Science and Information, pp. 369–387. Springer, Cham (2014)
Abada, L., Aouat, S.: Improved shape from shading without initial information. Front. Comput. Sci. 11(2), 320–331 (2017)
Lee, C.H., Rosenfeld, A.: Improved methods of estimating shape from shading using the light source coordinate system. Artif. Intell. 26, 125–143 (1985)
Prados, E., Faugeras, O.: Shape from shading: a well-posed problem? In: CVPR (2005)
Elhabian, S., Mostafa, E., Rara, H., Farag, A.: Non-Lambertian Model-based Facial Shape Recovery from Single Image Under Unknown General Illumination (2012)
Tankus, A., Sochen, N., Yeshurun, Y.: Perspective shape-from-shading by fast marching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (vol. I), Washington, DC, USA, pp. 43–49 (2004)
Ikeuchi, K., Horn, B.K.P.: Numerical shape from shading and occluding boundaries. Artif. Intell. 17(1–3), 141–184 (1981)
Pentland, A.P.: Local shading analysis. IEEE Trans. Patt. Anal. Mach. Intell. 6(2), 170–187 (1984)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bourahla, O.E.F., Debbah, A.M., Abada, L., Aouat, S. (2021). Shape From Shading: A Non-iterative Method Using Neural Networks. In: Abraham, A., Hanne, T., Castillo, O., Gandhi, N., Nogueira Rios, T., Hong, TP. (eds) Hybrid Intelligent Systems. HIS 2020. Advances in Intelligent Systems and Computing, vol 1375. Springer, Cham. https://doi.org/10.1007/978-3-030-73050-5_74
Download citation
DOI: https://doi.org/10.1007/978-3-030-73050-5_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73049-9
Online ISBN: 978-3-030-73050-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)