cvpr cvpr2013 cvpr2013-427 cvpr2013-427-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Wangmeng Zuo, Lei Zhang, Chunwei Song, David Zhang
Abstract: Image denoising is a classical yet fundamental problem in low level vision, as well as an ideal test bed to evaluate various statistical image modeling methods. One of the most challenging problems in image denoising is how to preserve the fine scale texture structures while removing noise. Various natural image priors, such as gradient based prior, nonlocal self-similarity prior, and sparsity prior, have been extensively exploited for noise removal. The denoising algorithms based on these priors, however, tend to smooth the detailed image textures, degrading the image visual quality. To address this problem, in this paper we propose a texture enhanced image denoising (TEID) method by enforcing the gradient distribution of the denoised image to be close to the estimated gradient distribution of the original image. A novel gradient histogram preservation (GHP) algorithm is developed to enhance the texture structures while removing noise. Our experimental results demonstrate that theproposed GHP based TEID can well preserve the texture features of the denoised images, making them look more natural.
[1] H. Attouch, J. Bolte, P. Redont, and A. Soubeyran. Proximal alternating minimization and projection methods for nonconvex problems: An approach based on the KurdykaLojasiewicz inequality. Mathematics of Operations Research, 35(2):438–457, 2010.
[2] A. Buades, B. Coll, and J. Morel. A review of image denoising methods, with a new one. Multiscale Model. Simul., 4(2):490–530, 2005.
[3] H. C. Burger, C. J. Schuler, and S. Harmeling. Image denoising: can plain neural networks compete with bm3d? Proc. CVPR, 2012.
[4] T. S. Cho, N. Joshi, C. L. Zitnick, S. B. Kang, R. Szeliski, and W. T. Freeman. A content-aware image prior. Proc. CVPR, 2010.
[5] T. S. Cho, C. L. Zitnick, N. Joshi, S. B. Kang, R. Szeliski, and W. T. Freeman. Image restoration by matching gradient distributions. IEEE T-PAMI, 34(4):683–694, 2012.
[6] I. Daubechies, M. Defriese, and C. DeMol. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math., 57(1 1): 1413–1457, 2004.
[7] W. Dong, L. Zhang, and G. Shi. Centralized sparse representation for image restoration. Proc. ICCV, 2011.
[8] W. Dong, L. Zhang, G. Shi, and X. Wu. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE T-IP, 20(7): 1838–1857, 2011.
[9] M. Elad and M. Aharon. Image denoising via sparse and redundant representations over learned dictionaries. IEEE T-IP, 15(12):3736–3745, 2006.
[10] R. Fergus, B. Singh, A. Hertzmann, S. Roweis, and W. T. Freeman. Removing camera shake from a single photograph. Proc. ACM SIGGRAPH, 2006.
[11] B. Georgescu, I. Shimshoni, and P. Meer. Mean shift based clustering in high dimensions: A texture classification example. Proc. ICCV, 2003.
[12] R. C. Gonzalez and R. E. Woods. Digital image processing. Beijing: Publishing House of Electronics Industry, 2005.
[13] E. Hadjidemetriou, M. D. Grossberg, and S. K. Nayar. Multiresolution histograms and their use for recognition. IEEE T-PAMI, 26(7):831–847, 2004.
[14] J. Jancsary, S. Nowozin, and C. Rother. Loss-specific training of non-parametric image restoration models: a new state
[15]
[16]
[17]
[18]
[19]
[20]
[21]
[22]
[23]
[24]
[25]
[26] of the art. Proc. ECCV, 2012. N. Joshi, C. L. Zitnick, R. Szeliski, and D. Kriegman. Image deblurring and denoising using color priors. Proc. CVPR, 2009. V. Katkovnik, A. Foi, K. Egiazarian, and J. Astola. From local kernel to nonlocal multiple-model image denoising. IJCV, 86(1): 1–32, 2010. D. Krishnan and R. Fergus. Fast image deconvolution using hyper-laplacian priors. Proc. NIPS, 2009. A. Levin, R. Fergus, F. Durand, and W. T. Freeman. Image and depth from a conventional camera with a coded aperture. Proc. ACM SIGGRAPH, 2007. A. Levin, Y. Weiss, F. Durand, and W. T. Freeman. Efficient marginal likelihood optimization in blind deconvolution. Proc. CVPR, 2011. J. Mairal, F. Bach, and J. Ponce. Task-driven dictionary learning. IEEE T-PAMI, 32(4):791–804, 2012. J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman. Non-local sparse models for image restoration. Proc. ICCV, 2009. J. K. Patel and C. B. Read. Handbook of the normal distribution. New York: Marcel Dekker, 1982. J. Portilla, V. Strela, M. J. Wainwright, and E. P. Simoncelli. Image denoising using a scale mixture of gaussians in the wavelet domain. IEEE T-IP, 12(1 1): 1338–1351, 2003. S. Roth and M. J. Black. Fields of experts: a framework for learning image priors. Proc. CVPR, 2005. L. Rudin, S. Osher, and E. Fatemi. Nonlinear total variation based noise removal algorithms. Physica D, 60(1-4):259– 268, 1992. K. Suzuki, I. Horiba, and N. Sugie. Efficient approximation
[27]
[28]
[29]
[30] [3 1]
[32] of neural filters for removing quantum noise from images. IEEE T-SP, 50(7): 1787–1799, 2002. M. Varma and A. Zisserman. Classifying images of materials: achieving viewpoint and illumination independence. Proc. ECCV, 2002. M. Varma and A. Zisserman. A statistical approach to texture classification from single images. IJCV, 62(1-2):61–81, 2005. M. Wainwright and S. Simoncelli. Scale mixtures of gaussians and the statistics of natural images. Proc. NIPS, 1999. Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE T-IP, 13(4):600–612, 2004. M. Welling, G. Hinton, and S. Osindero. Learning sparse topographic representations with products of student-t distributions. Proc. NIPS, 2002. D. Zoran and Y. Weiss. From learning models of natural image patches to whole image restoration. Proc. ICCV, 2011. 11111222220000079977 Figure 4. Methods comparison. (a) Noisy image with AWGN of standard deviation 30; (b) SAPCA-BM3D [16] restoration result; (c) LSSC [21] restoration result; (d) CSR [7] restoration result; (e) GHP restoration result; (f) ground truth. Figure 5. Results comparison with and without segmentation. (a) Top: noisy image with AWGN of standard deviation 30; bottom: a two-region segmentation of it; (b) SAPCA-BM3D [16] restoration results; (c) GHP restoration results without segmentation; (d) GHP restoration results with segmentation; (e) ground truth. 1 1 12 2 20 01 80 8