Abstract
We propose a solution to the problem of inferring the depth map, radiance and motion of a scene from a collection of motion-blurred and defocused images. We model motion-blur and defocus as an anisotropic diffusion process, whose initial conditions depend on the radiance and whose diffusion tensor encodes the shape of the scene, the motion field and the optics parameters. We show that this model is well-posed and propose an efficient algorithm to infer the unknowns of the model. Inference is performed by minimizing the discrepancy between the measured blurred images and the ones synthesized via forward diffusion. Since the problem is ill-posed, we also introduce additional Tikhonov regularization terms. The resulting method is fast and robust to noise as shown by experiments with both synthetic and real data.
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
Aubert, G., Kornprobst, P.: Mathematical Problems in Image Processing. Springer, Heidelberg (2002)
Baker, S., Kanade, T.: Limits on super-resolution and how to break them. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(9), 1167–1183 (2002)
Bascle, B., Blake, A., Zisserman, A.: Motion deblurring and super-resolution from an image sequence. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 573–582. Springer, Heidelberg (1996)
Ben-Ezra, M., Nayar, S.K.: Motion deblurring using hybrid imaging. In: Computer Vision and Pattern Recognition, vol. 1, pp. 657–664 (2003)
Bertero, M., Boccacci, P.: Introduction to inverse problems in imaging. Institute of Physics Publishing, Bristol (1998)
Chaudhuri, S., Rajagopalan, A.: Depth from defocus: a real aperture imaging approach. Springer, Heidelberg (1999)
Engl, H., Hanke, M., Neubauer, A.: Regularization of Inverse Problems. Kluwer Academic Publishers, Dordrecht (1996)
Ens, J., Lawrence, P.: An investigation of methods for determining depth from focus. IEEE Trans. Pattern Anal. Mach. Intell. 15, 97–108 (1993)
Favaro, P., Burger, M., Soatto, S.: Scene and motion reconstruction from defocused and motion-blurred images via anisotropic diffusion. In: UCLA - Math. Dept. Technical Report (cam03-63) (November 2003)
Favaro, P., Osher, S., Soatto, S., Vese, L.: 3d shape from anisotropic diffusion. In: Intl. Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 179–186 (2003)
Heeger, D.J., Jepson, A.D.: Subspace methods for recovering rigid motion i. Int. J. of Computer Vision 7(2), 95–117 (1992)
Pentland, A.: A new sense for depth of field. IEEE Trans. Pattern Anal. Mach. Intell. 9, 523–531 (1987)
Perona, P., Malik, J.: Scale space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(7), 629–639 (1990)
Rav-Acha, A., Peleg, S.: Restoration of multiple images with motion blur in different directions. In: IEEE Workshop on Applications of Computer Vision (WACV), Palm-Springs (2000)
Subbarao, M., Surya, G.: Depth from defocus: a spatial domain approach. Intl. J. of Computer Vision 13, 271–294 (1994)
Tschumperle, D., Deriche, R.: Vector-valued image regularization with pde’s: A common framework for different applications. In: CVPR 2003, pp. I:651–656 (2003)
Watanabe, M., Nayar, S.: Rational filters for passive depth from defocus. Intl. J. of Comp. Vision 27(3), 203–225 (1998)
Weickert, J.: Anisotropic Diffusion in Image Processing. B.G.Teubner, Stuttgart (1998)
Xiong, Y., Shafer, S.: Depth from focusing and defocusing. In: Proc. of the Intl. Conf. of Comp. Vision and Pat. Recogn., pp. 68–73 (1993)
Yitzhaky, Y., Milberg, R., Yohaev, S., Kopeika, N.S.: Comparison of direct blind deconvolution methods for motion-blurred images. In: Applied Optics-IP, July 1999, vol. 38, pp. 4325–4332 (1999)
You, Y., Kaveh, M.: Blind image restoration by anisotropic diffusion. IEEE Trans. on Image Processing 8(3), 396–407 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Favaro, P., Burger, M., Soatto, S. (2004). Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3021. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24670-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-24670-1_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21984-2
Online ISBN: 978-3-540-24670-1
eBook Packages: Springer Book Archive