Abstract
This paper presents a fast deblurring method that produces a deblurring result from a single image of moderate size in a few seconds. We accelerate both latent image estimation and kernel estimation in an iterative deblurring process by introducing a novel prediction step and working with image derivatives rather than pixel values. In the prediction step, we use simple image processing techniques to predict strong edges from an estimated latent image, which will be solely used for kernel estimation. With this approach, a computationally efficient Gaussian prior becomes sufficient for deconvolution to estimate the latent image, as small deconvolution artifacts can be suppressed in the prediction. For kernel estimation, we formulate the optimization function using image derivatives, and accelerate the numerical process by reducing the number of Fourier transforms needed for a conjugate gradient method. We also show that the formulation results in a smaller condition number of the numerical system than the use of pixel values, which gives faster convergence. Experimental results demonstrate that our method runs an order of magnitude faster than previous work, while the deblurring quality is comparable. GPU implementation facilitates further speed-up, making our method fast enough for practical use.
- Ben-Ezra, M., and Nayar, S. K. 2004. Motion-based motion deblurring. IEEE Trans. Pattern Analysis Machine Intelligence 26, 6, 689--698. Google ScholarDigital Library
- Chan, T. F., and Wong, C.-K. 1998. Total variation blind deconvolution. IEEE Trans. Image Processing 7, 3, 370--375. Google ScholarDigital Library
- Chen, W.-G., Nandhakumar, N., and Martin, W. N. 1996. Image motion estimation from motion smear - a new computational model. IEEE Trans. Pattern Analysis Machine Intelligence 18, 4, 412--425. Google ScholarDigital Library
- Cho, S., Matsushita, Y., and Lee, S. 2007. Removing non-uniform motion blur from images. In Proc. ICCV 2007, 1--8.Google Scholar
- Dai, S., and Wu, Y. 2008. Motion from blur. In Proc. CVPR 2008, 1--8.Google Scholar
- Fergus, R., Singh, B., Hertzmann, A., Roweis, S. T., and Freeman, W. 2006. Removing camera shake from a single photograph. ACM Trans. Graphics 25, 3, 787--794. Google ScholarDigital Library
- Hou, Q., Zhou, K., and Guo, B. 2008. BSGP: bulksynchronous GPU programming. ACM Trans. Graphics 27, 3, article no. 19. Google ScholarDigital Library
- Ji, H., and Liu, C. 2008. Motion blur identification from image gradients. In Proc. CVPR 2008, 1--8.Google Scholar
- Jia, J. 2007. Single image motion deblurring using transparency. In Proc. CVPR 2007, 1--8.Google ScholarCross Ref
- Joshi, N., Szeliski, R., and Kreigman, D. 2008. PSF estimation using sharp edge prediction. In Proc. CVPR 2008, 1--8.Google Scholar
- Joshi, N. 2008. Enhancing photographs using content-specific image priors. PhD thesis, UCSD. Google ScholarDigital Library
- Levin, A., Fergus, R., Durand, F., and Freeman, W. T. 2007. Image and depth from a conventional camera with a coded aperture. ACM Trans. Graphics 26, 3, article no. 70. Google ScholarDigital Library
- Levin, A., Sand, P., Cho, T. S., Durand, F., and Freeman, W. T. 2008. Motion-invariant photography. ACM Trans. Graphics 27, 3, article no. 71. Google ScholarDigital Library
- Levin, A., Weiss, Y., Durand, F., and Freeman, W. 2009. Understanding and evaluating blind deconvolution algorithms. In Proc. CVPR 2009, 1--8.Google Scholar
- Lucy, L. 1974. An iterative technique for the rectification of observed distributions. Astronomical Journal 79, 6, 745--754.Google ScholarCross Ref
- Money, J. H., and Kang, S. H. 2008. Total variation minimizing blind deconvolution with shock filter reference. Image and Vision Computing 26, 2, 302--314. Google ScholarDigital Library
- Osher, S., and Rudin, L. I. 1990. Feature-oriented image enhancement using shock filters. SIAM Journal on Numerical Analysis 27, 4, 919--940. 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
- Shan, Q., Jia, J., and Agarwala, A. 2008. High-quality motion deblurring from a single image. ACM Trans. Graphics 27, 3, article no. 73. Google ScholarDigital Library
- Tai, Y.-W., Du, H., Brown, M. S., and Lin, S. 2008. Image/video deblurring using a hybrid camera. In Proc. CVPR 2008, 1--8.Google Scholar
- Tomasi, C., and Manduchi, R. 1998. Bilateral filtering for gray and color images. In Proc. ICCV 1998, 839--846. Google ScholarDigital Library
- Wiener, N. 1964. Extrapolation, Interpolation, and Smoothing of Stationary Time Series. MIT Press. Google ScholarDigital Library
- Yitzhaky, Y., Mor, I., Lantzman, A., and Kopeika, N. S. 1998. Direct method for restoration of motion-blurred images. Journal of Opt. Soc. Am. A. 15, 6, 1512--1519.Google ScholarCross Ref
- Yuan, L., Sun, J., Quan, L., and Shum, H.-Y. 2007. Image deblurring with blurred/noisy image pairs. ACM Trans. Graphics 26, 3, article no. 1. Google ScholarDigital Library
- Yuan, L., Sun, J., Quan, L., and Shum, H.-Y. 2008. Progressive inter-scale and intra-scale non-blind image deconvolution. ACM Trans. Graphics 27, 3, article no. 74. Google ScholarDigital Library
Index Terms
- Fast motion deblurring
Recommendations
Fast motion deblurring
SIGGRAPH Asia '09: ACM SIGGRAPH Asia 2009 papersThis paper presents a fast deblurring method that produces a deblurring result from a single image of moderate size in a few seconds. We accelerate both latent image estimation and kernel estimation in an iterative deblurring process by introducing a ...
A novel gradient attenuation Richardson-Lucy algorithm for image motion deblurring
This paper presents a novel blind image deconvolution algorithm for motion deblurring from a single blurred image. We propose a unified framework for both blur kernel estimation and non-blind image deconvolution by using bilateral filtering (BF) and a ...
Blind motion deblurring using multiple images
Recovery of degraded images due to motion blurring is a challenging problem in digital imaging. Most existing techniques on blind deblurring are not capable of removing complex motion blurring from the blurred images of complex structures. One promising ...
Comments