The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.12 - December (2011 vol.33)
pp: 2354-2367
Anat Levin , Weizmann Institute of Science, Rehovot
Yair Weiss , The Hebrew University of Jerusalem, Jerusalem
Fredo Durand , Massachusetts Institute of Technology, Cambridge
William T. Freeman , Massachusetts Institute of Technology, Cambridge
ABSTRACT
Blind deconvolution is the recovery of a sharp version of a blurred image when the blur kernel is unknown. Recent algorithms have afforded dramatic progress, yet many aspects of the problem remain challenging and hard to understand. The goal of this paper is to analyze and evaluate recent blind deconvolution algorithms both theoretically and experimentally. We explain the previously reported failure of the naive MAP approach by demonstrating that it mostly favors no-blur explanations. We show that, using reasonable image priors, a naive simulations MAP estimation of both latent image and blur kernel is guaranteed to fail even with infinitely large images sampled from the prior. On the other hand, we show that since the kernel size is often smaller than the image size, a MAP estimation of the kernel alone is well constrained and is guaranteed to succeed to recover the true blur. The plethora of recent deconvolution techniques makes an experimental evaluation on ground-truth data important. As a first step toward this experimental evaluation, we have collected blur data with ground truth and compared recent algorithms under equal settings. Additionally, our data demonstrate that the shift-invariant blur assumption made by most algorithms is often violated.
INDEX TERMS
Blind deconvolution, motion deblurring, natrual image statistics, statistical estimation.
CITATION
Anat Levin, Yair Weiss, Fredo Durand, William T. Freeman, "Understanding Blind Deconvolution Algorithms", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 12, pp. 2354-2367, December 2011, doi:10.1109/TPAMI.2011.148
REFERENCES
[1] G.R. Ayers and J.C. Dainty, "Interative Blind Deconvolution Method and Its Applications," Optics Letters, vol. 13, pp. 547-549, 1988.
[2] D. Brainard and W. Freeman, "Bayesian Color Constancy," J. Optical Soc. of Am., vol. 14, pp. 1393-1411, 1997.
[3] M.M. Bronstein, A.M. Bronstein, M. Zibulevsky, and Y.Y. Zeevi, "Blind Deconvolution of Images Using Optimal Sparse Representations," IEEE Trans. Image Processing, vol. 14, no. 6, pp. 726-736, June 2005.
[4] S. Cho and S. Lee, "Fast Motion Deblurring," Proc. ACM SIGGRAPH, 2009.
[5] R. Fergus, B. Singh, A. Hertzmann, S.T. Roweis, and W.T. Freeman, "Removing Camera Shake from a Single Photograph," Proc. ACM SIGGRAPH, 2006.
[6] J.R. Fienup, "Phase Retrieval Algorithms: A Comparison," Applied Optics, vol. 21, pp. 2758-2769, Aug. 1982.
[7] R.W. Gerchberg and W.O. Saxton, "A Practical Algorithm for the Determination of Phase from Image and Diffraction Plane Pictures," Optik, vol. 35, pp. 237-246, 1972.
[8] D.N. Godard, "Self-Recovering Equalization and Carrier Tracking in Two-Dimensional Data Communication Systems," IEEE Trans. Comm., vol. 28, no. 11, pp. 1867-1875, Nov. 1980.
[9] R.C. Gonzalez and R.E. Woods, Digital Image Processing. Prentice Hall, Jan. 2002.
[10] M. Hayes, "The Reconstruction of a Multidimensional Sequence from the Phase or Magnitude of Its Fourier Transform," IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 30, no. 2, pp. 140-154, Apr. 1982.
[11] J. Jia, "Single Image Motion Deblurring Using Transparency," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[12] C.R. Johnson, P. Schniter, T.J. Endres, J.D. Behm, D.R. Brown, and R.A. Casas, "Blind Equalization Using the Constant Modulus Criterion: A Review," Proc. IEEE, vol. 86, no. 10, pp. 1927-1950, Oct. 1998.
[13] N. Joshi, R. Szeliski, and D. Kriegman, "PSF Estimation Using Sharp Edge Prediction," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[14] A.K. Katsaggelos and K.T. Lay, "Maximum Likelihood Blur Identification and Image Restoration Using the EM Algorithm," IEEE Trans. Signal Processing, vol. 39, no. 3, pp. 729-733, Mar. 1991.
[15] S.M. Kay, Fundamentals of Statistical Signal Processing: Estimation Theory. Prentice Hall, 1997.
[16] D. Kundur and D. Hatzinakos, "Blind Image Deconvolution," IEEE Signal Processing Magazine, vol. 13, no. 3, pp. 43-64, May 1996.
[17] R.G. Lane and R.H.T. Bates, "Automatic Multidimensional Deconvolution," J. Optical Soc. of Am. A, vol. 4, no. 1, pp. 180-188, 1987.
[18] A. Levin, "Blind Motion Deblurring Using Image Statistics," Proc. Advances in Neural Information Processing Systems, 2006.
[19] A. Levin, R. Fergus, F. Durand, and W. Freeman, "Image and Depth from a Conventional Camera with a Coded Aperture," Proc. ACM SIGGRAPH, 2007.
[20] A. Levin, Y. Weiss, F. Durand, and W.T. Freeman, "Understanding and Evaluating Blind Deconvolution Algorithms," Technical Report MIT-CSAIL-TR-2009-014, 2009.
[21] A.C. Likas and N.P. Galatsanos, "A Variational Approach for Bayesian Blind Image Deconvolution," IEEE Trans. Signal Processing, vol. 52, no. 8, pp. 2222-2233, Aug. 2004.
[22] J.W. Miskin and D.J.C. MacKay, "Ensemble Learning for Blind Image Separation and Deconvolution," Proc. Advances in Independent Component Analysis, 2000.
[23] R. Molina, A.K. Katsaggelos, J. Abad, and J. Mateos, "A Bayesian Approach to Blind Deconvolution Based on Dirichlet Distributions," Proc. IEEE Int'l Conf. Acoustics, Speech, and Signal Processing, 1997.
[24] S. Roth and M.J. Black, "Fields of Experts: A Framework for Learning Image Priors," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2005.
[25] O. Shalvi and E. Weinstein, "New Criteria for Blind Deconvolution of Nonminimum Phase Systems (Channels)," IEEE Trans. Information Theory, vol. 36, no. 2, pp. 312-321, Mar. 1990.
[26] Q. Shan, J. Jia, and A. Agarwala, "High-Quality Motion Deblurring from a Single Image," Proc. ACM SIGGRAPH, 2008.
[27] Q. Shan, W. Xiong, and J. Jia, "Rotational Motion Deblurring of a Rigid Object from a Single Image," Proc. IEEE 11th Int'l Conf. Computer Vision, 2007.
[28] E.P. Simoncelli, "Bayesian Denoising of Visual Images in the Wavelet Domain," Bayesian Inference in Wavelet Based Models, Springer-Verlag, 1999.
[29] E. Thiébaut and J.-M. Conan, "Strict A Priori Constraints for Maximum-Likelihood Blind Deconvolution," J. Optical Soc. of Am. A, vol. 12, no. 3, pp. 485-492, 1995.
[30] Y. Weiss and W.T. Freeman, "What Makes a Good Model of Natural Images?" Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[31] O. Whyte, J. Sivic, A. Zisserman, and J. Ponce, "Non-Uniform Deblurring for Shaken Images," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2010.
[32] L. Xu and J. Jia, "Two-Phase Kernel Estimation for Robust Motion Deblurring," Proc. 11th European Conf. Computer Vision, 2010.
24 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool