Abstract
We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized equation. For a N × N pixel grid, the subspace of all integrable gradient fields is of dimension N 2 – 1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) α-surfaces using binary weights, where the parameter α allows trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotropic treatment discounts noise while recovering salient features in reconstructions.
Chapter PDF
Similar content being viewed by others
Keywords
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
Horn, B.: Height and gradient from shading. Int’l J. Computer Vision 5, 37–75 (1990)
Horn, B.: Determining lightness from an image. Comput. Graphics, Image Processing 3, 277–299 (1974)
Fattal, R., Lischinski, D., Werman, M.: Gradient domain high dynamic range compression. ACM Trans. Graph. 21, 249–256 (2002)
Agrawal, A., Raskar, R., Nayar, S., Li, Y.: Removing photography artifacts using gradient projection and flash-exposure sampling. ACM Trans. Graph. 24, 828–835 (2005)
Forsyth, D.: Shape from texture and integrability. In: Proc. Int’l Conf. Computer Vision, pp. 447–452 (2001)
Belhumeur, P., Kriegman, D., Yuille, A.: The bas-relief ambiguity. Int’l J. Computer Vision 35, 33–44 (1999)
Simchony, T., Chellappa, R., Shao, M.: Direct analytical methods for solving poisson equations in computer vision problems. IEEE Trans. Pattern Anal. Machine Intell. 12, 435–446 (1990)
Frankot, R.T., Chellappa, R.: A method for enforcing integrability in shape from shading algorithms. IEEE Trans. Pattern Anal. Machine Intell. 10, 439–451 (1988)
Yuille, A., Snow, D.: Shape and albedo from multiple images using integrability. In: Proc. Conf. Computer Vision and Pattern Recognition, pp. 158–164 (1997)
Petrovic, N., Cohen, I., Frey, B., Koetter, R., Huang, T.: Enforcing integrability for surface reconstruction algorithms using belief propagation in graphical models. In: Proc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 743–748 (2001)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Machine Intell. 23, 643–660 (2001)
Kovesi, P.: Shapelets correlated with surface normals produce surfaces. In: Proc. Int’l Conf. Computer Vision, pp. 994–1001 (2005)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Machine Intell. 12, 629–639 (1990)
Charbonnier, P., Blanc-Feraud, L., Aubert, G., Barluad, M.: Deterministic edge-preserving regularization in computed imaging. IEEE Trans. Image Processing 6, 298–311 (1997)
Aubert, G., Kornprobst, P.: Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations. Applied Mathematical Sciences, vol. 147. Springer, Heidelberg (2002)
Karacali, B., Snyder, W.: Noise reduction in surface reconstruction from a given gradient field. Int’l J. Computer Vision 60, 25–44 (2004)
Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. of the ACM 24, 381–395 (1981)
Agrawal, A., Chellappa, R., Raskar, R.: An algebraic approach to surface reconstruction from gradient fields. In: Proc. Int’l Conf. Computer Vision, vol. 1, pp. 174–181 (2005)
Weickert, J.: Anisotropic Diffusion in Image Processing. PhD thesis, University of Kaiserslautern, Germany (1996)
Horovitz, I., Kiryati, N.: Depth from gradient fields and control points: Bias correction in photometric stereo. Image and Vision Computing 22, 681–694 (2004)
Kimmel, R., Yavneh, I.: An algebraic multigrid approach to image analysis. SIAM J. Sci. Comput. 24, 1218–1231 (2003)
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
Agrawal, A., Raskar, R., Chellappa, R. (2006). What Is the Range of Surface Reconstructions from a Gradient Field?. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3951. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744023_45
Download citation
DOI: https://doi.org/10.1007/11744023_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33832-1
Online ISBN: 978-3-540-33833-8
eBook Packages: Computer ScienceComputer Science (R0)