cvpr cvpr2013 cvpr2013-131 cvpr2013-131-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Uwe Schmidt, Carsten Rother, Sebastian Nowozin, Jeremy Jancsary, Stefan Roth
Abstract: Non-blind deblurring is an integral component of blind approaches for removing image blur due to camera shake. Even though learning-based deblurring methods exist, they have been limited to the generative case and are computationally expensive. To this date, manually-defined models are thus most widely used, though limiting the attained restoration quality. We address this gap by proposing a discriminative approach for non-blind deblurring. One key challenge is that the blur kernel in use at test time is not known in advance. To address this, we analyze existing approaches that use half-quadratic regularization. From this analysis, we derive a discriminative model cascade for image deblurring. Our cascade model consists of a Gaussian CRF at each stage, based on the recently introduced regression tree fields. We train our model by loss minimization and use synthetically generated blur kernels to generate training data. Our experiments show that the proposed approach is efficient and yields state-of-the-art restoration quality on images corrupted with synthetic and real blur.
[1] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik. Contour detection and hierarchical image segmentation. TPAMI, 33(5):898–916, 2011.
[2] A. Barbu. Learning real-time MRF inference for image denoising. CVPR 2009.
[3] M. J. Black and A. Rangarajan. On the unification of line processes, outlier rejection, and robust statistics with applications in early vision. IJCV, 19(1):57–91, 1996.
[4] H. C. Burger, C. J. Schuler, and S. Harmeling. Image denoising: Can plain neural networks compete with BM3D? CVPR 2012.
[5] P. Charbonnier, L. Blanc-F e´raud, G. Aubert, and M. Barlaud. Two deterministic half-quadratic regularization algorithms for computed imaging. ICIP 1994.
[6] S. Cho and S. Lee. Fast motion deblurring. ACM T. Graphics, 28(5), 2009.
[7] S. Cho, J. Wang, and S. Lee. Handling outliers in non-blind image deconvolution. ICCV 2011.
[8] R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis, and W. T. Freeman. Removing camera shake from a single photograph. ACM T. Graphics, 3(25), 2006.
[9] B. Fr¨ ohlich, E. Rodner, and J. Denzler. As time goes by—anytime semantic segmentation with iterative context forests. Pattern Recognition (DAGM) 2012.
[10] Q. Gao and S. Roth. How well do filter-based MRFs model natural images? Pattern Recognition (DAGM) 2012.
[11] D. Geman and G. Reynolds. Constrained restoration and the recovery of discontinuities. TPAMI, 14(3):367–383, 1992.
[12] D. Geman and C. Yang. Nonlinear image recovery with halfquadratic regularization. IEEE TIP, 4(7):932–946, 1995.
[13] G. A. Hinton, S. Osindero, and Y.-W. Teh. A fast learning algorithm for deep belief nets. Neural Comput., 18: 1527–1554, 2006.
[14] J. Jancsary, S. Nowozin, and C. Rother. Loss-specific training ofnonparametric image restoration models: A new state of the art. ECCV 2012.
[15] J. Jancsary, S. Nowozin, T. Sharp, and C. Rother. Regression tree fields – an efficient, non-parametric approach to image labeling problems. CVPR 2012.
[16] R. K ¨ohler, M. Hirsch, B. Mohler, B. Sch o¨lkopf, and S. Harmeling. Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database. ECCV 2012.
[17] D. Krishnan and R. Fergus. Fast image deconvolution using hyperLaplacian priors. NIPS*2009.
[18] A. Levin, R. Fergus, F. Durand, and W. T. Freeman. Image and depth from a conventional camera with a coded aperture. ACM T. Graphics, 26(3):70:1–70:9, 2007.
[19] A. Levin, Y. Weiss, F. Durand, and W. T. Freeman. Efficient marginal likelihood optimization in blind deconvolution. CVPR 2011.
[20] A. Levin, Y. Weiss, F. Durand, and W. T. Freeman. Understanding and evaluating blind deconvolution algorithms. CVPR 2009.
[21] L. B. Lucy. An iterative technique for the rectification of observed distributions. The Astronom. Journal, 79:745, 1974.
[22] J. A. Palmer, D. P. Wipf, K. Kreutz-Delgado, and B. D. Rao. Variational EM algorithms for non-Gaussian latent variable models. NIPS*2005.
[23] W. Richardson. Bayesian-based iterative method of image restoration. J. Opt. Soc. America, 62(1):55–59, 1972.
[24] S. Roth and M. J. Black. Fields of experts. IJCV, 82(2):205–229, 2009.
[25] U. Schmidt, K. Schelten, and S. Roth. Bayesian deblurring with integrated noise estimation. CVPR 2011.
[26] Y.-W. Tai and S. Lin. Motion-aware noise filtering for deblurring of noisy and blurry images. CVPR 2012.
[27] M. Tappen, C. Liu, E. H. Adelson, and W. T. Freeman. Learning Gaussian conditional random fields for low-level vision. CVPR 2007.
[28] Z. Tu. Auto-context and its application to high-level vision tasks. CVPR 2008.
[29] M. J. Wainwright and E. P. Simoncelli. Scale mixtures of Gaussians and the statistics of natural images. NIPS*1999.
[30] L. Xu and J. Jia. Two-phase kernel estimation for robust motion deblurring. ECCV 2010. [3 1] L. Yuan, J. Sun, L. Quan, and H.-Y. Shum. Progressive inter-scale and intra-scale non-blind image deconvolution. ACM T. Graphics, 27(3), 2008. 666100 919