Abstract
We formulate a robust method using Expectation Maximization (EM) to address the problem of dense photometric stereo. Previous approaches using Markov Random Fields (MRF) utilized a dense set of noisy photometric images for estimating an initial normal to encode the matching cost at each pixel, followed by normal refinement by considering the neighborhood of the pixel. In this paper, we argue that they had not fully utilized the inherent data redundancy in the dense set and that its full exploitation leads to considerable improvement. Using the same noisy and dense input, this paper contributes in learning relevant observations, recovering accurate normals and very good surface albedos, and inferring optimal parameters in an unifying EM framework that converges to an optimal solution and has no free user-supplied parameter to set. Experiments show that our EM approach for dense photometric stereo outperforms the previous approaches using the same input.
This work was supported by the Research Grant Council of Hong Kong Special Administrative Region, China, under grant # 62005.
Chapter PDF
Similar content being viewed by others
Keywords
- Expectation Maximization
- Markov Random Field
- Expectation Maximization Algorithm
- Light Direction
- Photometric Stereo
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.
References
Woodham, R.: Photometric method for determining surface orientation from multiple images. OptEng 19(1), 139–144 (1980)
Coleman Jr., E., Jain, R.: Obtaining 3-dimensional shape of textured and specular surfaces using four-source photometry. CGIP 18(4), 309–328 (1982)
Solomon, F., Ikeuchi, K.: Extracting the shape and roughness of specular lobe objects using four light photometric stereo. PAMI 18(4), 449–454 (1996)
Lee, K., Kuo, C.: Shape reconstruction from photometric stereo. In: CVPR 1992, pp. 479–484 (1992)
Lim, J., Ho, J., Yang, M., Kriegman, D.: Passive photometric stereo from motion. In: ICCV 2005 (2005)
Tagare, H., de Figueiredo, R.: A theory of photometric stereo for a class of diffuse non-lambertian surfaces. PAMI 13(2), 133–152 (1991)
Kay, G., Caelly, T.: Estimating the parameters of an illumination model using photometric stereo. GMIP 57(5), 365–388 (1995)
Nayar, S., Ikeuchi, K., Kanade, T.: Determining shape and reflectance of hybrid surfaces by photometric sampling. IEEE Trans. on Robotics and Automation 6(4), 418–431 (1990)
Horn, B., Woodham, R., Silver, W.: Determining shape and reflectance using multiple images. In: MIT AI Memo (1978)
Hertzmann, A., Seitz, S.: Shape and materials by example: a photometric stereo approach. In: CVPR 2003, vol. I, pp. 533–540 (2003)
Drbohlav, O., Sara, R.: Unambiguous determination of shape from photometric stereo with unknown light sources. In: ICCV 2001 (2001)
Tang, K., Tang, C., Wong, T.: Dense photometric stereo using tensorial belief propagation. In: CVPR 2005, vol. 1, pp. 132–139 (2005)
Wu, T., Tang, C.: Dense photometric stereo using a mirror sphere and graph cut. In: CVPR 2005, vol. 1, pp. 140–147 (2005)
Bilmes, J.: A gentle tutorial on the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Technical Report ICSI-TR-97-021, ICSI (1997)
Kovesi, P.: Shapelets correlated with surface normals produce surfaces. In: ICCV 2005 (2005)
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
Wu, TP., Tang, CK. (2006). Dense Photometric Stereo by Expectation Maximization. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3954. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744085_13
Download citation
DOI: https://doi.org/10.1007/11744085_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33838-3
Online ISBN: 978-3-540-33839-0
eBook Packages: Computer ScienceComputer Science (R0)