Abstract
We present a new algorithm for removing motion blur from a single image. Our method computes a deblurred image using a unified probabilistic model of both blur kernel estimation and unblurred image restoration. We present an analysis of the causes of common artifacts found in current deblurring methods, and then introduce several novel terms within this probabilistic model that are inspired by our analysis. These terms include a model of the spatial randomness of noise in the blurred image, as well a new local smoothness prior that reduces ringing artifacts by constraining contrast in the unblurred image wherever the blurred image exhibits low contrast. Finally, we describe an effficient optimization scheme that alternates between blur kernel estimation and unblurred image restoration until convergence. As a result of these steps, we are able to produce high quality deblurred results in low computation time. We are even able to produce results of comparable quality to techniques that require additional input images beyond a single blurry photograph, and to methods that require additional hardware.
Supplemental Material
- Ben-Ezra, M., and Nayar, S. K. 2004. Motion-based motion deblurring. TPAMI 26, 6, 689--698. Google ScholarDigital Library
- Bracewell, R. N. 1999. The Fourier Transform and Its Applications. McGraw-Hill.Google Scholar
- Donatelli, M., Estatico, C., Martinelli, A., and Serra-Capizzano, S. 2006. Improved image deblurring with antireflective boundary conditions and re-blurring. Inverse Problems 22, 6, 2035--2053.Google ScholarCross Ref
- Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T., and Freeman, W. 2006. Removing camera shake from a single photograph. ACM Transactions on Graphics 25, 787--794. Google ScholarDigital Library
- Gamelin, T. W. 2003. Complex Analysis. Springer.Google Scholar
- Jia, J. 2007. Single image motion deblurring using transparency. In CVPR.Google Scholar
- Kim, S. K., and Paik, J. K. 1998. Out-of-focus blur estimation and restoration for digital auto-focusing system. Electronics Letters 34, 12, 1217--1219.Google ScholarCross Ref
- Kim, S.-J., Koh, K., Lustig, M., and Boyd, S. 2007. An efficient method for compressed sensing. In ICIP.Google Scholar
- Levin, A., Fergus, R., Durand, F., and Freeman, B. 2007. Image and depth from a conventional camera with a coded aperture. In SIGGRAPH. Google ScholarDigital Library
- Likas, A., and Galatsanos, N. 2004. A Variational Approach for Bayesian Blind Image Deconvolution. IEEE Transactions on Signal Processing 52, 8, 2222--2233. Google ScholarDigital Library
- Liu, R., and Jia, J. 2008. Reducing boundary artifacts in image deconvolution. In ICIP.Google Scholar
- Lucy, L. 1974. Bayesian-based iterative method of image restoration. Journal of Astronomy 79, 745--754.Google ScholarCross Ref
- Miskin, J., and MacKay, D. 2000. Ensemble learning for blind image separation and deconvolution. Advances in Independent Component Analysis, 123--141.Google Scholar
- Neelamani, R., Choi, H., and Baraniuk, R. G. 2004. ForWaRD: Fourier-wavelet regularized deconvolution for ill-conditioned systems. IEEE Transactions on Signal Processing 52, 418--433. Google ScholarDigital Library
- Raskar, R., Agrawal, A., and Tumblin, J. 2006. Coded exposure photography: Motion deblurring using fluttered shutter. ACM Transactions on Graphics 25, 3, 795--804. Google ScholarDigital Library
- Rav-Acha, A., and Peleg, S. 2005. Two motion blurred images are better than one. Pattern Recognition Letters 26, 311--317. Google ScholarDigital Library
- Roth, S., and Black, M. J. 2005. Fields of experts: A framework for learning image priors. In CVPR. Google ScholarDigital Library
- Shan, Q., Xiong, W., and Jia, J. 2007. Rotational motion deblurring of a rigid object from a single image. In ICCV.Google Scholar
- Simon, M. K. 2002. Probability Distributions Involving Gaussian Random Variables: A Handbook for Engineers, Scientists and Mathematicians. Springer. Google ScholarDigital Library
- Wainwright, M. J. 2006. Estimating the "wrong" graphical model: Benefits in the computation-limited setting. Journal of Machine Learning Research, 1829--1859. Google ScholarDigital Library
- Weiss, Y., and Freeman, W. T. 2007. What makes a good model of natural images? In CVPR.Google Scholar
- Wiener, N. 1964. Extrapolation, Interpolation, and Smoothing of Stationary Time Series. MIT Press. Google ScholarDigital Library
- Yuan, L., Sun, J., Quan, L., and Shum, H.-Y. 2007. Image Deblurring with Blurred/Noisy Image Pairs. In SIGGRAPH. Google ScholarDigital Library
Index Terms
- High-quality motion deblurring from a single image
Recommendations
High-quality image deblurring with panchromatic pixels
Image deblurring has been a very challenging problem in recent decades. In this article, we propose a high-quality image deblurring method with a novel image prior based on a new imaging system. The imaging system has a newly designed sensor pattern ...
Single-image motion deblurring using an adaptive image prior
Blind deblurring is the restoration of a sharp image from a blurred image when the blur kernel is unknown. Most image deblurring algorithms impose a uniform sparse gradient prior on the whole image, and reconstruct the image with piecewise smooth ...
High-quality non-blind image deconvolution with adaptive regularization
Non-blind image deconvolution is a process that obtains a sharp latent image from a blurred image when a point spread function (PSF) is known. However, ringing and noise amplification are inevitable artifacts in image deconvolution since perfect PSF ...
Comments