cvpr cvpr2013 cvpr2013-17 cvpr2013-17-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Christian J. Schuler, Harold Christopher Burger, Stefan Harmeling, Bernhard Schölkopf
Abstract: Image deconvolution is the ill-posed problem of recovering a sharp image, given a blurry one generated by a convolution. In this work, we deal with space-invariant non- blind deconvolution. Currently, the most successful meth- ods involve a regularized inversion of the blur in Fourier domain as a first step. This step amplifies and colors the noise, and corrupts the image information. In a second (and arguably more difficult) step, one then needs to remove the colored noise, typically using a cleverly engineered algorithm. However, the methods based on this two-step ap- proach do not properly address the fact that the image information has been corrupted. In this work, we also rely on a two-step procedure, but learn the second step on a large dataset of natural images, using a neural network. We will show that this approach outperforms the current state-ofthe-art on a large dataset of artificially blurred images. We demonstrate the practical applicability of our method in a real-world example with photographic out-of-focus blur.
[1] Noise, dynamic range and bit depth in digital slrs. http : / / theory .uchi cago . edu / ˜e jm/pix / 2 0 d/ t e st s /noi se / . By Emil Martinec, updated May 2008. 5
[2] S. Boyd and L. Vandenberghe. Convex optimization. Cambridge university press, 2004. 2
[3] H. C. Burger, C. J. Schuler, and S. Harmeling. Image denoising: Can plain neural networks compete with bm3d? IEEE Conf. Comput. Vision and Pattern Recognition, pages 2392– 2399, 2012. 2, 3, 4
[4] H. C. Burger, C. J. Schuler, and S. Harmeling. Image denoising with multi-layer perceptrons, part 1: comparison with existing algorithms and with bounds. arXiv:1211.1544, 2012. 2
[5] H. C. Burger, C. J. Schuler, and S. Harmeling. Image denoising with multi-layer perceptrons, part 2: training trade-offs and analysis of their mechanisms. arXiv:1211.1552, 2012. 6
[6] S. Cho and S. Lee. Fast motion deblurring. In ACM Trans. Graphics, volume 28, page 145. ACM, 2009. 2
[7] S. Cho, J. Wang, and S. Lee. Handling outliers in non-blind image deconvolution. In IEEE Int. Conf. Comput. Vision, 2011. 5
[8] D. C. Cire ¸san, U. Meier, L. M. Gambardella, and J. Schmidhuber. Deep, big, simple neural nets for handwritten digit recognition. Neural Computation, 22(12):3207–3220, 2010. 3
[9] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process., 16(8):2080–2095, 2007.
[10]
[11]
[12]
[13]
[14]
[15]
[16]
[17]
[18]
[19] 2, 5 K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian. Image restoration by sparse 3d transform-domain collaborative filtering. In Soc. Photo-Optical Instrumentation Engineers, volume 6812, page 6, 2008. 1, 2, 3, 4, 5, 6 A. Danielyan, V. Katkovnik, and K. Egiazarian. Bm3d frames and variational image deblurring. IEEE Trans. Image Process., 21(4): 1715–1728, 2012. 2, 3, 4, 5, 6 M. Elad and M. Aharon. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. on Image Process., 15(12):3736–3745, 2006. 2, 7 D. Erhan, A. Courville, and Y. Bengio. Understanding representations learned in deep architectures. Technical report, 1355, Universit e´ de Montr ´eal/DIRO., 2010. 6, 7 J. Guerrero-Col o´n, L. Mancera, and J. Portilla. Image restoration using space-variant gaussian scale mixtures in overcomplete pyramids. IEEE Trans. Image Process., 17(1):27–41, 2008. 2, 3 M. Hirsch, C. Schuler, S. Harmeling, and B. Scholkopf. Fast removal of non-uniform camera shake. In IEEE Int. Conf. Comput. Vision, pages 463–470. IEEE, 2011. 3 V. Jain and H. Seung. Natural image denoising with convolutional networks. Advances Neural Inform. Process. Syst., 21:769–776, 2008. 2 J. Jancsary, S. Nowozin, and C. Rother. Loss-specific training of non-parametric image restoration models: A new state of the art. In Europ. Conf. Comput. Vision. IEEE, 2012. 8 D. Krishnan and R. Fergus. Fast image deconvolution using hyper-Laplacian priors. InAdvances Neural Inform. Process. Syst., 2009. 2, 4, 5, 6 Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-
[20]
[21]
[22]
[23]
[24]
[25]
[26]
[27]
[28]
[29] based learning applied to document recognition. Proc. IEEE, 86(1 1):2278–2324, 1998. 2, 3 A. Levin, R. Fergus, F. Durand, and W. Freeman. Deconvolution using natural image priors. 26(3), 2007. 2, 5, 6 A. Levin, Y. Weiss, F. Durand, and W. T. Freeman. Understanding and evaluating blind deconvolution algorithms. In IEEE Conf. Comput. Vision and Pattern Recognition, pages 1964–1971. IEEE, 2009. 4 M. M ¨akitalo and A. Foi. Optimal inversion of the anscombe transformation in low-count poisson image denoising. IEEE Trans. Image Process. , 20(1):99–109, 2011. 5 J. Portilla, V. Strela, M. Wainwright, and E. Simoncelli. Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE Trans. Image Process., 12(1 1): 1338– 1351, 2003. 2 S. Roth and M. Black. Fields of experts. Int. J. Comput. Vision, 82(2):205–229, 2009. 2 D. Rumelhart, G. Hinton, and R. Williams. Learning representations by back-propagating errors. Nature, 323(6088):533–536, 1986. 3 U. Schmidt, K. Schelten, and S. Roth. Bayesian deblurring with integrated noise estimation. In IEEE Conf. Comput. Vision and Pattern Recognition, pages 2625–2632. IEEE, 2011. 2, 5 P. Sermanet and Y. LeCun. Traffic sign recognition with multi-scale convolutional networks. In IEEE Int. Joint Conf. Neural Networks, pages 2809–2813. IEEE, 2011. 3 E. Simoncelli and E. Adelson. Noise removal via bayesian wavelet coring. In IEEE Int. Conf. Image Process., volume 1, pages 379–382. IEEE, 1996. 2 P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P. Man- zagol. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learning Research, 11:3371–3408, 2010. 2, 7
[30] J. Xie, L. Xu, and E. Chen. Image denoising and inpainting with deep neural networks. Advances Neural Inform. Process. Syst., 26: 1–8, 2012. 2 [3 1] D. Zoran and Y. Weiss. From learning models of natural image patches to whole image restoration. In IEEE Int. Conf. Comput. Vision, pages 479–486. IEEE, 2011. 2, 5, 6 11111000007777724422