基于统计分析的图像去模糊与图像去噪新方法研究
|
摘要
图像恢复是计算机视觉领域的一个重要研究课题。拍摄环境中光照条件不充分时，相机往往需要较长的曝光时间使图像充分曝光，而长时间曝光则易引起图像运动模糊。另一方面，相机可以通过设置高感光度，提升传感器的光线敏感度来减少曝光时间并避免图像模糊。然而，高感光度会放大图像噪声，使图像噪点突出并影响图像质量。图像模糊和图像噪声干扰均可看作清晰图像的退化。本文对这两类图像退化进行研究，并提出有效的图像恢复算法。
对于图像直线运动模糊，本文分析了直线运动模糊在空域和频域的方向性高频能量分布特性，提出了基于方向性高通滤波的模糊特征分析框架。基于提出的方向性高通滤波，本文方法可有效判别图像模糊区域，估计图像模糊方向，较传统模糊方向估计方法更为简洁并且准确。对于更普遍的非直线运动模糊，本文分析了自然场景图像和文本图像梯度分布统计特征的差异性。根据图像统计特征，本文提出了基于梯度域的图像盲反卷积以及结合图像局部上下界约束的文本图像恢复算法。实验显示本文提出的文本图像去模糊实现了比同类算法更优的恢复效果。
同时，本文进一步分析了图像去模糊问题假设模型的可靠性。对于空不变模糊，传统图像去模糊方法往往假定模糊图像由清晰图像和点扩散函数线性卷积得到，然而实际情况下相机响应函数在图像生成过程中会使模糊图像偏离卷积模型。因此线性卷积模型应用于实际图像去模糊时，存在模型近似误差，基于该假设条件的图像反卷积也会引起图像振铃。本文探讨了相机响应函数对图像反卷积的影响，尤其是对图像低频和高频区域的不同扰动，并理论分析了卷积模型引入的误差和误差界。此外，本文根据清晰图像和模糊图像的灰度分布特征提出了相机响应函数估计算法。
图像去噪方面，非局部均值和BM3D等基于图像块相似性的图像去噪是目前比较流行的算法。这类算法能有效滤除图像噪声，但由于图像块相似性匹配计算量过大，实时运算很困难。针对计算量大的缺点，本文提出基于图像块测地线距离的图像去噪算法。通过研究图像块测地线距离最短路径的性质，本文提出图像块距离的快速近似计算，并采用多尺度算法实现图像去噪。本文提出的算法与非局部均值算法性能相当，但计算效率远高于该算法以及其他基于图像块相似度的图像去噪算法。
Image restoration has been a long-standing problem in computer vision. Under low-lightconditions, a camera requires either long exposure or a high ISO setting in order to obtain abright image. However, long exposure will result in image motion blur, and high ISO will amplifynoises in the captured image. These two situations can be regarded as image degradation. In thispaper, image restoration methods are proposed to estimate sharp and clean image from acaptured blurry or noisy image.
For image motion blur, the properties of linear motion blur in spatial and frequency domainare investigated. The directional high-pass filter is proposed to identify motion direction anddetect motion blurred regions. Specifically, a closed-form solution for motion directionestimation is derived. Regarding general motion blur, this paper studied the gradient statistics ofnatural-scene images and document images. Gradient domain blind deconvolution is proposedand content-aware document image deblurring is presented. Image local constraints areconsidered in order to suppress ringing artifacts. The results produced by the proposed methodsare comparable to that of the state-of-the-art methods.
A common assumption in image deblurring is that a blurry image is a linear convolution resultof a sharp image by a Point Spread Function. Nevertheless, in a real camera system, theconvolution is carried out in irradiance domain and Camera Response Function (CRF) willnonlinearly map the convolved irradiance to the output intensity image. This paper presents acomprehensive study on the effects of CRFs on motion deblurring. The approximation errorcaused by the direct intensity convolution is analyzed. We prove that the intensity-basedconvolution closely approximates the irradiance model at low frequency regions, but it will havelarge deviation at high frequency regions. Then, we further propose a CRF estimation methodbased on a pair of sharp/blurred images.
Finally, image denoising problem is reviewed. Patch-based denoising, like Non-Local Means(NLM) and BM3D, is able to produce high-quality result. However, they require expensivepair-wise patch comparisons. This paper introduces a Patch Geodesic (PG) distance metric forpatch comparison. In order to reduce noise at multiple scales, we adopt Laplacian-Gaussianimage decomposition and apply PG-based denoising at each scale. It achieves comparable qualityas the state-of-the-art methods. Since PG path can be efficiently approximated by minimum hoppath, the proposed method is a few orders of magnitude faster than traditional patch-baseddenoising methods without losing quality.
对于图像直线运动模糊，本文分析了直线运动模糊在空域和频域的方向性高频能量分布特性，提出了基于方向性高通滤波的模糊特征分析框架。基于提出的方向性高通滤波，本文方法可有效判别图像模糊区域，估计图像模糊方向，较传统模糊方向估计方法更为简洁并且准确。对于更普遍的非直线运动模糊，本文分析了自然场景图像和文本图像梯度分布统计特征的差异性。根据图像统计特征，本文提出了基于梯度域的图像盲反卷积以及结合图像局部上下界约束的文本图像恢复算法。实验显示本文提出的文本图像去模糊实现了比同类算法更优的恢复效果。
同时，本文进一步分析了图像去模糊问题假设模型的可靠性。对于空不变模糊，传统图像去模糊方法往往假定模糊图像由清晰图像和点扩散函数线性卷积得到，然而实际情况下相机响应函数在图像生成过程中会使模糊图像偏离卷积模型。因此线性卷积模型应用于实际图像去模糊时，存在模型近似误差，基于该假设条件的图像反卷积也会引起图像振铃。本文探讨了相机响应函数对图像反卷积的影响，尤其是对图像低频和高频区域的不同扰动，并理论分析了卷积模型引入的误差和误差界。此外，本文根据清晰图像和模糊图像的灰度分布特征提出了相机响应函数估计算法。
图像去噪方面，非局部均值和BM3D等基于图像块相似性的图像去噪是目前比较流行的算法。这类算法能有效滤除图像噪声，但由于图像块相似性匹配计算量过大，实时运算很困难。针对计算量大的缺点，本文提出基于图像块测地线距离的图像去噪算法。通过研究图像块测地线距离最短路径的性质，本文提出图像块距离的快速近似计算，并采用多尺度算法实现图像去噪。本文提出的算法与非局部均值算法性能相当，但计算效率远高于该算法以及其他基于图像块相似度的图像去噪算法。
Image restoration has been a long-standing problem in computer vision. Under low-lightconditions, a camera requires either long exposure or a high ISO setting in order to obtain abright image. However, long exposure will result in image motion blur, and high ISO will amplifynoises in the captured image. These two situations can be regarded as image degradation. In thispaper, image restoration methods are proposed to estimate sharp and clean image from acaptured blurry or noisy image.
For image motion blur, the properties of linear motion blur in spatial and frequency domainare investigated. The directional high-pass filter is proposed to identify motion direction anddetect motion blurred regions. Specifically, a closed-form solution for motion directionestimation is derived. Regarding general motion blur, this paper studied the gradient statistics ofnatural-scene images and document images. Gradient domain blind deconvolution is proposedand content-aware document image deblurring is presented. Image local constraints areconsidered in order to suppress ringing artifacts. The results produced by the proposed methodsare comparable to that of the state-of-the-art methods.
A common assumption in image deblurring is that a blurry image is a linear convolution resultof a sharp image by a Point Spread Function. Nevertheless, in a real camera system, theconvolution is carried out in irradiance domain and Camera Response Function (CRF) willnonlinearly map the convolved irradiance to the output intensity image. This paper presents acomprehensive study on the effects of CRFs on motion deblurring. The approximation errorcaused by the direct intensity convolution is analyzed. We prove that the intensity-basedconvolution closely approximates the irradiance model at low frequency regions, but it will havelarge deviation at high frequency regions. Then, we further propose a CRF estimation methodbased on a pair of sharp/blurred images.
Finally, image denoising problem is reviewed. Patch-based denoising, like Non-Local Means(NLM) and BM3D, is able to produce high-quality result. However, they require expensivepair-wise patch comparisons. This paper introduces a Patch Geodesic (PG) distance metric forpatch comparison. In order to reduce noise at multiple scales, we adopt Laplacian-Gaussianimage decomposition and apply PG-based denoising at each scale. It achieves comparable qualityas the state-of-the-art methods. Since PG path can be efficiently approximated by minimum hoppath, the proposed method is a few orders of magnitude faster than traditional patch-baseddenoising methods without losing quality.
引文
[1] http://nssdc.gsfc.nasa.gov/nmc/spacecraftDisplay.do?id=1969-014A
[2] D. Kurdur, D. Zinakos. Blind image deconvolution, IEEE Single Processing Magazine,13(5):43-64,1996
[3] Y. Tai, Motion-aware noise filtering for deblurring of noisy and blurry images, in CVPR,2012.
[4] Y. Tsin, V. Ramesh, T. Kanade, Statistical Calibration of CCD Imaging Process, in ICCV,2001.
[5] R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis, and W. T. Freeman. Removing camerashake from a single photograph. ACM Transactions on Graphics,(7):787–794,2006
[6] Q. Shan, J. Jia, and A. Agarwala. High-quality motion deblurring from a single image, inSIGGRAPH,2008.
[7] J. Cai, H. Ji, C. Liu and Z. Shen. Blind motion deblurring from a single image using sparseapproximation, in CVPR,2009.
[8] J. Jia. Single image motion deblurring using transparency, in CVPR,2007.
[9] N. Joshi, R. Szeliski, and D. Kriegman. PSF estimation using sharp edge prediction, inCVPR,2008.
[10] S. Zhuo, D. Guo, T. Sim, Robust Flash Deblurring, in CVPR2010
[11] D. Krishnan, R. Fergus, Dark Flash Photography, in SIGGRAPH2009,
[12] L. Yuan, J. Sun, L. Quan and H. Shum. Image deblurring with blurred/noisy image pairs,SIGGRAPH,2007.
[13] L. Yuan，J. Sun，L. Quan，H. Shum. Blurred/non-blurred image alignment using sparsenessprior, in ICCV,2007
[14] M. Ben-ezra, K. Nayar. Motion-based motion deblurring, IEEE Transactions on PatternAnalysis and Machine Intelligence,(6):689-698,2004
[15] J. Chen, L. Yuan, C. Tang, and L. Quan. Robust dual motion deblurring, in CVPR,2008.
[16] J. Cai, H. Ji, C. Liu and Z. Shen. High-quality curvelet-based motion deblurring from animage pair, in CVPR,2009.
[17] F. Rooms, M. Ronsse, A. Pizurica, et al. PSF estimation with application in autofocus andimage restoration, IEEE Benelux Signal Processing Symposium, pp:13-16,2002.
[18]邸慧,于起峰.基于自相关的匀速运动模糊尺度参数识别,国防科技大学学报,(5):123-125,2006
[19] Y. Yitzhaky, A. Lantzman, I. Moret al. Evaluation of the PSF from motion blurred images,Image Processing and Hardware,(3):822-831,1997
[20] W. T. Freeman and E. H. Adelson. The design and use of steerable filters, Pattern Analysisand Machine Intelligence,(9):891–906,1991
[21] W. Fawwaz Al Maki, S. Sugimoto. Blind deconvolution algorithm for spatially-invariantmotion blurred images based on inverse filtering and DST, International Journal of Circuits,Systems and Signal Processing,(1):92-100,2007
[22]M. E. Moghaddam and M. Jamzad. Motion blur identification in noisy images usingmathematical models and statistical measures, Pattern Recognition,(7):1946-1957,2007
[23] L.B. Lucy. An iterative technique for the rectification of observed distributions.Astronomical Journal,(7):745-754,1974
[24] W. H. Richardson. Bayesian-based iterative method of image restoration, Journal of theOptical Society of America,1972,1,55-59.
[25] R. C. Gonzalez and R. E. Woods. Digital image processing, Pearson Education,2003.
[26]孙辉,张葆,刘晶红.基于维纳滤波的运动模糊消除算法及其在航空成像系统中的应用,光学精密工程,(12)735-740,2005
[27] Y. Wang, J. Yang, W. Yin, and Y. Zhang. A new alternating minimization algorithm fortotal variation image reconstruction. SIAM Journal of Imaging Sciences,(7):248–272,2008
[28] U. Schmidt, C. Rother, S. Nowozin, J. Jancsary, and S. Roth, Discriminative Non-blindDeblurring, in CVPR,2013
[29] S. Cho, J. Wang, and S. Lee. Handling outliers in non-blind image, deconvolution. In ICCV,2011.
[30] L. Yuan, J. Sun, L. Quan, and H. Shum. Progressive inter-scale and intra-scale non-blindimage deconvolution. ACM T. Graphics,27(3):1354-1261,2008.
[31] T Cho, L. Zitnick, N. Joshi, S. Kang,R. Szeliski, and W. T. Freeman, Image Restoration byMatching Gradient Distributions, IEEE Transactions on Pattern Analysis and MachineIntelligence,34(4): pp.683-694,2012
[32] X. Chen, J. Yang, Q. Wu. Image deblur in gradient domain, Optical Engineering,(10):117003-117003-7,2010
[33] S. Cho and S. Lee. Fast motion deblurring. ACM T. Graphics,28(5),2009.
[34] L. Sun, S. Cho, J. Wang, J. Hays, Edge-based Blur Kernel Estimation Using Patch Priors，in:ICCP，2013
[35] Y. Tai, H. Du, M. Brown, S. Lin. Correction of spatially varying image and video motionblur using a hybrid camera, IEEE Transactions on Pattern Analysis and Machine Intelligence,(7):1012-1028,2009
[36]毛成军，李奇，徐之海.任意运动形式模糊图像的恢复，光子学报，8,2126-2129,2009
[37] M. Tico, M. Trimeche, M. Vehvilainen. Motion blur identification based on differentlyexposed images, in ICIP,2006.
[38] C. Liu, W. T. Freeman, R. Szeliski, and S. B. Kang. Noise estimation from a single image.In CVPR,2006.
[39] H．Burger, C. Schuler, S. Harmeling, Image denoising: Can plain Neural Networks competewith BM3D, in CVPR,2012.
[40] Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli,"Image quality assessment: Fromerror visibility to structural similarity," IEEE Transactions on Image Processing, vol.13, no.4,pp.600-612, Apr.2004.
[41] P. Marziliano, F. Dufaux, S. Winkler and T. Ebrahimi, a no-reference perceptual blur metric,ICIP002
[42] E．Ong. W. Lin, Z. Lu, X.Yang, S. Yao, F. Pan, L. Jiarrg, and F. Moscheni, A no-referencequality metric for measuring image blur, International Symposium on Signal Processing and ItsApplications,2003
[43]左博新,明德烈,敖争光,郑文娟，基于图像结构的无参考模糊图像及其复原图像质量评价方法，地理信息世界，2(1):13-20,2008
[44]王虹,潘晓露,李一民,汪虹,一种基于梯度幅度值的图像质量客观评价方法,光学与光电技术，12, Vol.2, No.6:23-25,2004
[45] H. R. Wu and M. Yuen. A generalized block edge impairment metric for video coding.IEEE Signal Processing Letters,4(11):317-320,1997
[46] A. K. Moorthy, A. C. Bovik, A Two-Step Framework for Constructing Blind Image QualityIndices, Signal Processing Letters, IEEE, Vol.17, No.5.(May2010), pp.513-516
[47] H. Lin and K. Li.“Motion blur removal and its application to vehicle speed detection,”IEEE International Conference on Image Processing, Oct.2004.
[48] S. Dai, M. Yang, Y. Wu, A. Katsaggelos,“Tracking motion blurred targets in video,” IEEEInternational Conference on Image Processing, Oct.2006.
[49] P. Favoro and S. Soatto,“A variational approach to scene reconstruction and imagesegmentation from motion blur cues,” IEEE Conference on Computer Vision and PatternRecognition, June,2004.
[50] Q. Shan, W. Xiong, and J. Jia,“Rotational motion deblurring of a rigid object from asingle image,” In IEEE International Conference on Computer Vision,2007.
[51] O. Whyte, J. Sivic, A. Zisserman, J. Ponce,“Non-uniform Deblurring for Shaken Images,”In CVPR,2010.
[52] Y. Yitzhaky, I. Mor, A. Lantzman, and N. S. Kopeika,“Direct method for restoration ofmotion blurred images,” Journal of the Optical Society of America. A, Optics and image science,15(6):1512–1519,1998.
[53] F. Krahmer, Y. Lin, B. McAdoo, etc.“Blind image deconvolution: motion blur estimation,”Tech. Rep., University of Minnesota,2006.
[54] Y. Yitzhaky, N. S. Kopeika,“Identification of blur parameters from motion blurredimages,” Graphical models and image processing, Vol.59, No.5, pp.310-320, September1997.
[55] J. Biemond, R. Lagendijk and R. Mersereau. Iterative methods for image deblurring,Proceedings of the IEEE, Vol.78, Issue5, pp.856–883,1990.
[56] D. Slepian,“Restoration of photographs blurred by image motion,” Bell Syst. Tech. J.46,2353–2362,1967.
[57] M. Cannon,“Blind deconvolution of spatially invariant image blurs with phase,” IEEETrans. Acoust. Speech Signal Process. ASSP-24,1976.
[58] J. Oliveira, M. Figueiredo, and J. Bioucas-Dias,“Blind estimation of motion blurparameters for image deconvolution,” Lecture Notes in Computer Science,2007
[59] M. Masry A scalable wavelet-based video distortion metric and applications, IEEETransactions on Circuits and Systems for Video Technology, Volume16, pp.260–273,2006
[60] R. Liu, Z. Li, J. Jia,“Image partial blur detection and classification,” in IEEE Conferenceon Computer Vision and Pattern Recognition,(CVPR),2008.
[61] A. Levin,“Blind motion deblurring using image statistics,” in Neural InformationProcessing Systems (NIPS),2006.
[62] R.J. Hanisch, R.L. White, R.L. Gilliland, Deconvolution of images and spectra. AcademicPress, California,1997.
[63] S. Schuon, K. Diepold. Comparison of motion de-blur algorithms and real worlddeployment, Acta Astronautica, pp:1050-1065,2009
[64] D. Krishnan, R. Fergus, Fast Image Deconvolution using Hyper-Laplacian Priors, in: NIPS,2009
[65] N. Joshi, C. Zitnick, R. Szeliski, D. Kriegman, Image deblurring and denoising using colorpriors, In CVPR2009.
[66] A. Levin, R. Fergus, F. Durand, and W. T. Freeman. Image and depth from a conventionalcamera with a coded aperture. ACM Transactions on Graphics,26(31):70:1–70:9,2007.
[67] Y. You and M. Kaveh, Blind Image Restoration by Anisotropic Regularization, IEEETransactions on Image Processing, vol.8, no.3, pp:396-407,1999.
[68] T. F. Chan and C. K. Wong, Total Variation Blind Deconvolution, IEEE Transactions onImage Processing, vol.7, no.3, pp:370-375,1998.
[69] Christian J. Schuler, Harold Christopher Burger, Stefan Harmeling, and Bernhard Schlkopf,“A machine learning approach for non-blind image deconvolution”, CVPR2013
[70] D. Zoran and Y. Weiss. From learning models of natural image patches to whole imagerestoration. In ICCV,2011.
[71] X. Chen, F. Li, J. Yang, J. Yu, A Theoretical Analysis of Camera Response Functions inImage Deblurring, European Conference on Computer Vision, in: ECCV,2012.
[72] S. Kim, H. Lin, Z. Lu, S. Susstrunk, S. Lin, M. S. Brown. A New In-Camera ImagingModel for Color Computer Vision and its Application. IEEE Transactions on Pattern Analysisand Machine Intelligence (TPAMI),34(2), pp.2289-2302,2012
[73] A. Levin, Y. Weiss, F. Durand and W. T. Freeman. Understanding and evaluating blinddeconvolution algorithms, In CVPR2009.
[74] M. Brown and W. Seales, Image restoration of arbitrarily warped documents, IEEETran. PAMI, VOL.26, NO.10, pp:1295-1306,2004
[75] L. Zhang, A. Yip and C. Tan, Removing shading distortions in camera-based documentimages using inpainting and surface fitting with radial basis functions, in ICDAR2007.
[76] L. Likforman-Sulem, J. Darbon and E. Barney Smith, Pre-processing of degraded printeddocuments by non-local means and total variation, in ICDAR2009.
[77] Y. Tian and W. Ming, Adaptive deblurring for camera-based document image processing,Lecture Notes in Computer Science,2009, Volume5876, pp:767-777,2009
[78] L. Kenneth G, Text image deblurring by high-probability word selection, US Patent6282324, Publication Date2001.
[79] X. Qi, L. Zhang, C. Tan, Motion deblurring for optical character recognition, inICDAR2005.
[80] A. Gupta, N. Joshi, C. Zitnick, M. Cohen, B. Curless. Single image deblurring using motiondensity functions. In ECCV2010.
[81] J. Bardsley, S. Jefferies, J. Nagy, and R. Plemmons, Blind iterative restoration of imageswith spatially-varying blur, Opt. Express14, pp:1767–1782,2006
[82] S. Babacan, R. Molina, and A. Katsaggelos, Variational bayesian blind deconvolution usinga total variation prior, IEEE Transactions on Image Processing, Volume18,Issue1,18(1):12-26,2009.
[83] T. Bishop, R. Molina, and J. R. Hopgood, Blind restoration of blurred photographs via ARmodelling and MCMC, in ICIP2008.
[84] T. Kanungo and Q. Zheng, Estimating degradation model parameters using neighborhoodpattern distributions: an optimization approach, IEEE Trans. PAMI. Volume26, Issue4, pp:520-524,2004.
[85] X. Chen, X. He, J. Yang, and Q. Wu. An effective document image deblurring algorithm, In:CVPR,2011
[86] H. Cho and J. Wang and S. Lee, Text Image Deblurring Using Text-Specific Properties,ECCV,2012.
[87] T. Kasar, J. Kumar and A. Ramakrishnan, Font and background color independent textbinarization，In: ICDAR,2007.
[88] J. S. Valverde and R. R. Grigat, Optimum binarization of technical document images, In:ICIP,2000.
[89] F. Drira, F. LeBourgeois, and H. Emptoz，A coupled mean shift-anisotropic diffusionapproach for document image segmentation and restoration, ICDAR, pp:814-818,2007
[90] C. Gopalan and D.Manjula, Sliding window approach based text binarisation from complextextual images, International Journal on Computer Science and Engineering, Vol.02, No.02,pp:309-313,2010
[91] S. Osher, M. Burger, D. Goldfarb, J. Xu, W. Yin, An iterative regularization method fortotal variation-based image restoration, Multiscale Modeling&Simulation, Vol.4, No.2. pp.460-489.2005
[92] R. Jian, et al., Machine vision, MIT Press and McGraw-Hill, Inc,1995.
[93] Krishnan, D., Tay, T., Fergus, R, Blind deconvolution using a normalized sparsity measure.In: CVPR2011
[94] Y. Tai, S. Lin, Motion-aware noise filtering for deblurring of noisy and blurry image, In:CVPR2012.
[95] P. Debevec, J. Malik, Recovering high dynamic range radiance maps from photographs. In:SIGGRAPH,1997
[96] Y. Chang, J. Reid, RGB calibration for color image-analysis in machine vision. IEEE Trans.on IP5:1414-1422,1996
[97] Mitsunaga, T., Nayar, S.K, Radiometric self calibration. In: CVPR (1999)
[98] Grossberg, M.D., Nayar, S.K, Modeling the space of camera response functions. IEEETrans. PAMI (26):1272-1282(2004)
[99] Kim, S.J., Pollefeys, M, Robust radiometric calibration and vignetting correction. IEEETrans. PAMI (30):562-576(2008)
[100] Kim, S., Frahm, J., Pollefeys, M, Radiometric calibration with illumination change foroutdoor scene analysis. In: CVPR (2008)
[101] Lin, S., Gu, J., Yamazaki, S., Shum, H.Y, Radiometric calibration from a single image. In:CVPR (2004)
[102] Lin, S., Zhang, L, Determining the radiometric response function from a single grayscaleimage. In: CVPR (2005)
[103] Y. Matsushita, S. Lin, Radiometric calibration from noise distributions. In: CVPR (2007)
[104] Kim, S., Tai, Y.W., Kim, S., Brown, M.S., Matsushita, Y, Nonlinear camera responsefunctions and image deblurring. In: CVPR (2012)
[105] Lee, J.Y., Shi, B., Matsushita, Y., Kweon, I.S., Ikeuchi, K, Radiometric calibration bytransform invariant low-rank structure. In: CVPR (2011)
[106] B. Wilburn, H. Xu, Y. Matsushita, Radiometric calibration using temporal irradiancemixtures. In: CVPR (2008)
[107] Y. Tai, X. Chen, S. Kim, S. Kim, F. Li, J. Yang, J. Yu, Y. Matsushita, M. Brown,Nonlinear Camera Response Functions and Image Deblurring: Theoretical Analysis and Practice.IEEE Trans Pattern Anal Mach Intell. Feb.35(10):2498-2512,2013.
[108] Farid, H, Blind inverse gamma correction. IEEE Transactions on Image Processing,10:1428-1433(2001)
[109] Ng, T.T., Chang, S.F., Tsui, M.P, Using geometry invariants for camera response functionestimation. In: CVPR (2007)
[110] L. I. Rudin, S. Osher, and E. Fatemi. Nonlinear total variation based noise removalalgorithms. Physica D: Nonlinear Phenomena,60:259–268,1992.
[111] P. Perona and J. Malik. Scale-space and edge detection using anisotropic diffusion. IEEETrans. PAMI.,12(7):629-639,1990.
[112] C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. In ICCV,1998.
[113] J. Portilla, V. Strela, M. J. Wainwright, and E. P. Simoncelli. Image denoising using scalemixtures of Gaussians in the wavelet domain. IEEE Trans. Imag. Proc.,12:1338—1351,2003.
[114] http://www.gris.informatik.tudarmstadt.de/sroth/research/foe.
[115] A. Buades and B. Coll. A non-local algorithm for image denoising. In CVPR,2005.
[116] V. K. Kostadin Dabov, Alessandro Foi and K. Egiazarian. Image denoising withblock-matching and3d filtering. In Proc. SPIE6064,606414(2006), pages454–467.
[117] L. Zhang, W. Dong, D. Zhang, and G. Shi. Two-stage image denoising by principalcomponent analysis with local pixel grouping. Pattern Recogn.,43(4):1531–1549,2010.
[118] A. Adams, N. Gelfand, J. Dolson, and M. Levoy. Gaussian kd-trees for fasthigh-dimensional filtering. ACM Trans.Graph.,28:21:1–21:12,2009.
[119] X. Bai and G. Sapiro. A geodesic framework for fast interactive image and videosegmentation and matting. In ICCV,2007.
[120] P. J. Burt and E. H. Adelson. Readings in computer vision: issues, problems, principles,and paradigms.1987.
[121] Q. Yang, K.-H. Tan, and N. Ahuja. Real-time o(1) bilateral filtering. In CVPR, pages557–564,2009.
[122] Q. Yang. Recursive bilateral filtering. In ECCV,2012.
[123] F. Durand and J. Dorsey. Fast bilateral filtering for the display of high-dynamic-rangeimages, pages:257-266,2002.
[124] A. Criminisi, T. Sharp, C. Rother, and P. P’erez. Geodesic image and video editing. ACMTrans. Graph.,29:790-804,2010.
[125] G. A. Pierre Charbonnier, Laure Blanc-Feraud and M. Barlaud. Deterministicedge-preserving regularization in computed imaging. IEEE Trans. on Imag. Proc.,6(2):298-311,1997
[126] D. Barash. A fundamental relationship between bilateral filtering, adaptive smoothing, andthe nonlinear diffusion equation. IEEE Trans. PAMI.,24(6):844–847,2002.
[127] S. Roth and M. J. Black. Fields of experts: A framework for learning image priors. InCVPR, pages860–867,2005.
[128] Weiss, Y., Freeman,W.T, What makes a good model of natural images? In:CVPR (2007).
[129] S. Paris and F. Durand. A fast approximation of the bilateral filter using a signalprocessing approach. IJCV,81:568--580,2006.
[130] B. Weiss. Fast median and bilateral filtering. ACM Trans. Graph.,25(3):519–526, July2006.
[131] F. Porikli. Constant time O(1) bilateral filtering. In CVPR,2008.
[132] N. Kumar, L. Zhang, and S. Nayar. What is a good nearest neighbors algorithm for findingsimilar patches in images? In ECCV,2008.
[133] T. Brox, O. Kleinschmidt, and D. Cremers. Efficient nonlocal means for denoising oftextural patterns. IEEE Trans. On Imag. Proc.17(7):1083–1092,2008.
[134] K. He and J. Sun. Computing nearest-neighbor fields via propagation-assisted kd-trees. InCVPR,2012.
[135] V. Gulshan, C. Rother, A. Criminisi, A. Blake, and A. Zisserman. Geodesic star convexityfor interactive image segmentation. In CVPR,2010.
[136] A. Criminisi, T. Sharp, and A. Blake. Geos: Geodesic image segmentation. In ECCV,2008.
[137] J. Grazzini and P. Soille. Edge-preserving smoothing using a similarity measure inadaptive geodesic neighbourhoods. Pattern Recogn.,42(10):2306–2316,2009.
[138] L. Yatziv, L. Yatziv, G. Sapiro, and G. Sapiro. Fast image and video colorization usingchrominance blending. IEEE Trans. on Imag. Proc.,15(5):1120-1129,2006.
[139] X. Bai and G. Sapiro. Geodesic matting: A framework for fast interactive image and videosegmentation and matting. Int. J. Comput. Vision,82(2):113–132, Apr.2009.
[140] D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented naturalimages and its application to evaluating segmentation algorithms and measuring ecologicalstatistics. In ICCV,2001.
[141] L. Condat. A Simple Trick to Speed Up and Improve the Non-Local Means, Technicalreport, GREYC laboratory, Centre national de la recherché scientifique (CNRS), France,2010.
[142] A. Foi, V. Katkovnik, and K. Egiazarian. Pointwise shape adaptive dct for high-qualitydenoising and deblocking of grayscale and color images, IEEE Transactions on ImageProcessing,16(5):1395-1411,2007
[143] Markku Makitalo, Alessandro Foi, Optimal Inversion of the Anscombe Transformation inLow-Count Poisson Image Denoising, IEEE Transactions on Image Processing,20(1):99-1092011
[144] Bo Zhang, Mohamed-Jalal Fadili, and Jean-Luc Starck, Wavelets, Ridgelets, andCurvelets for Poisson Noise Removal, IEEE Transactions on Image Processing,17(7):1093-1108,2008
[145] http://www.neatimage.com.
[146] http://www.picturecode.com.
[2] D. Kurdur, D. Zinakos. Blind image deconvolution, IEEE Single Processing Magazine,13(5):43-64,1996
[3] Y. Tai, Motion-aware noise filtering for deblurring of noisy and blurry images, in CVPR,2012.
[4] Y. Tsin, V. Ramesh, T. Kanade, Statistical Calibration of CCD Imaging Process, in ICCV,2001.
[5] R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis, and W. T. Freeman. Removing camerashake from a single photograph. ACM Transactions on Graphics,(7):787–794,2006
[6] Q. Shan, J. Jia, and A. Agarwala. High-quality motion deblurring from a single image, inSIGGRAPH,2008.
[7] J. Cai, H. Ji, C. Liu and Z. Shen. Blind motion deblurring from a single image using sparseapproximation, in CVPR,2009.
[8] J. Jia. Single image motion deblurring using transparency, in CVPR,2007.
[9] N. Joshi, R. Szeliski, and D. Kriegman. PSF estimation using sharp edge prediction, inCVPR,2008.
[10] S. Zhuo, D. Guo, T. Sim, Robust Flash Deblurring, in CVPR2010
[11] D. Krishnan, R. Fergus, Dark Flash Photography, in SIGGRAPH2009,
[12] L. Yuan, J. Sun, L. Quan and H. Shum. Image deblurring with blurred/noisy image pairs,SIGGRAPH,2007.
[13] L. Yuan，J. Sun，L. Quan，H. Shum. Blurred/non-blurred image alignment using sparsenessprior, in ICCV,2007
[14] M. Ben-ezra, K. Nayar. Motion-based motion deblurring, IEEE Transactions on PatternAnalysis and Machine Intelligence,(6):689-698,2004
[15] J. Chen, L. Yuan, C. Tang, and L. Quan. Robust dual motion deblurring, in CVPR,2008.
[16] J. Cai, H. Ji, C. Liu and Z. Shen. High-quality curvelet-based motion deblurring from animage pair, in CVPR,2009.
[17] F. Rooms, M. Ronsse, A. Pizurica, et al. PSF estimation with application in autofocus andimage restoration, IEEE Benelux Signal Processing Symposium, pp:13-16,2002.
[18]邸慧,于起峰.基于自相关的匀速运动模糊尺度参数识别,国防科技大学学报,(5):123-125,2006
[19] Y. Yitzhaky, A. Lantzman, I. Moret al. Evaluation of the PSF from motion blurred images,Image Processing and Hardware,(3):822-831,1997
[20] W. T. Freeman and E. H. Adelson. The design and use of steerable filters, Pattern Analysisand Machine Intelligence,(9):891–906,1991
[21] W. Fawwaz Al Maki, S. Sugimoto. Blind deconvolution algorithm for spatially-invariantmotion blurred images based on inverse filtering and DST, International Journal of Circuits,Systems and Signal Processing,(1):92-100,2007
[22]M. E. Moghaddam and M. Jamzad. Motion blur identification in noisy images usingmathematical models and statistical measures, Pattern Recognition,(7):1946-1957,2007
[23] L.B. Lucy. An iterative technique for the rectification of observed distributions.Astronomical Journal,(7):745-754,1974
[24] W. H. Richardson. Bayesian-based iterative method of image restoration, Journal of theOptical Society of America,1972,1,55-59.
[25] R. C. Gonzalez and R. E. Woods. Digital image processing, Pearson Education,2003.
[26]孙辉,张葆,刘晶红.基于维纳滤波的运动模糊消除算法及其在航空成像系统中的应用,光学精密工程,(12)735-740,2005
[27] Y. Wang, J. Yang, W. Yin, and Y. Zhang. A new alternating minimization algorithm fortotal variation image reconstruction. SIAM Journal of Imaging Sciences,(7):248–272,2008
[28] U. Schmidt, C. Rother, S. Nowozin, J. Jancsary, and S. Roth, Discriminative Non-blindDeblurring, in CVPR,2013
[29] S. Cho, J. Wang, and S. Lee. Handling outliers in non-blind image, deconvolution. In ICCV,2011.
[30] L. Yuan, J. Sun, L. Quan, and H. Shum. Progressive inter-scale and intra-scale non-blindimage deconvolution. ACM T. Graphics,27(3):1354-1261,2008.
[31] T Cho, L. Zitnick, N. Joshi, S. Kang,R. Szeliski, and W. T. Freeman, Image Restoration byMatching Gradient Distributions, IEEE Transactions on Pattern Analysis and MachineIntelligence,34(4): pp.683-694,2012
[32] X. Chen, J. Yang, Q. Wu. Image deblur in gradient domain, Optical Engineering,(10):117003-117003-7,2010
[33] S. Cho and S. Lee. Fast motion deblurring. ACM T. Graphics,28(5),2009.
[34] L. Sun, S. Cho, J. Wang, J. Hays, Edge-based Blur Kernel Estimation Using Patch Priors，in:ICCP，2013
[35] Y. Tai, H. Du, M. Brown, S. Lin. Correction of spatially varying image and video motionblur using a hybrid camera, IEEE Transactions on Pattern Analysis and Machine Intelligence,(7):1012-1028,2009
[36]毛成军，李奇，徐之海.任意运动形式模糊图像的恢复，光子学报，8,2126-2129,2009
[37] M. Tico, M. Trimeche, M. Vehvilainen. Motion blur identification based on differentlyexposed images, in ICIP,2006.
[38] C. Liu, W. T. Freeman, R. Szeliski, and S. B. Kang. Noise estimation from a single image.In CVPR,2006.
[39] H．Burger, C. Schuler, S. Harmeling, Image denoising: Can plain Neural Networks competewith BM3D, in CVPR,2012.
[40] Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli,"Image quality assessment: Fromerror visibility to structural similarity," IEEE Transactions on Image Processing, vol.13, no.4,pp.600-612, Apr.2004.
[41] P. Marziliano, F. Dufaux, S. Winkler and T. Ebrahimi, a no-reference perceptual blur metric,ICIP002
[42] E．Ong. W. Lin, Z. Lu, X.Yang, S. Yao, F. Pan, L. Jiarrg, and F. Moscheni, A no-referencequality metric for measuring image blur, International Symposium on Signal Processing and ItsApplications,2003
[43]左博新,明德烈,敖争光,郑文娟，基于图像结构的无参考模糊图像及其复原图像质量评价方法，地理信息世界，2(1):13-20,2008
[44]王虹,潘晓露,李一民,汪虹,一种基于梯度幅度值的图像质量客观评价方法,光学与光电技术，12, Vol.2, No.6:23-25,2004
[45] H. R. Wu and M. Yuen. A generalized block edge impairment metric for video coding.IEEE Signal Processing Letters,4(11):317-320,1997
[46] A. K. Moorthy, A. C. Bovik, A Two-Step Framework for Constructing Blind Image QualityIndices, Signal Processing Letters, IEEE, Vol.17, No.5.(May2010), pp.513-516
[47] H. Lin and K. Li.“Motion blur removal and its application to vehicle speed detection,”IEEE International Conference on Image Processing, Oct.2004.
[48] S. Dai, M. Yang, Y. Wu, A. Katsaggelos,“Tracking motion blurred targets in video,” IEEEInternational Conference on Image Processing, Oct.2006.
[49] P. Favoro and S. Soatto,“A variational approach to scene reconstruction and imagesegmentation from motion blur cues,” IEEE Conference on Computer Vision and PatternRecognition, June,2004.
[50] Q. Shan, W. Xiong, and J. Jia,“Rotational motion deblurring of a rigid object from asingle image,” In IEEE International Conference on Computer Vision,2007.
[51] O. Whyte, J. Sivic, A. Zisserman, J. Ponce,“Non-uniform Deblurring for Shaken Images,”In CVPR,2010.
[52] Y. Yitzhaky, I. Mor, A. Lantzman, and N. S. Kopeika,“Direct method for restoration ofmotion blurred images,” Journal of the Optical Society of America. A, Optics and image science,15(6):1512–1519,1998.
[53] F. Krahmer, Y. Lin, B. McAdoo, etc.“Blind image deconvolution: motion blur estimation,”Tech. Rep., University of Minnesota,2006.
[54] Y. Yitzhaky, N. S. Kopeika,“Identification of blur parameters from motion blurredimages,” Graphical models and image processing, Vol.59, No.5, pp.310-320, September1997.
[55] J. Biemond, R. Lagendijk and R. Mersereau. Iterative methods for image deblurring,Proceedings of the IEEE, Vol.78, Issue5, pp.856–883,1990.
[56] D. Slepian,“Restoration of photographs blurred by image motion,” Bell Syst. Tech. J.46,2353–2362,1967.
[57] M. Cannon,“Blind deconvolution of spatially invariant image blurs with phase,” IEEETrans. Acoust. Speech Signal Process. ASSP-24,1976.
[58] J. Oliveira, M. Figueiredo, and J. Bioucas-Dias,“Blind estimation of motion blurparameters for image deconvolution,” Lecture Notes in Computer Science,2007
[59] M. Masry A scalable wavelet-based video distortion metric and applications, IEEETransactions on Circuits and Systems for Video Technology, Volume16, pp.260–273,2006
[60] R. Liu, Z. Li, J. Jia,“Image partial blur detection and classification,” in IEEE Conferenceon Computer Vision and Pattern Recognition,(CVPR),2008.
[61] A. Levin,“Blind motion deblurring using image statistics,” in Neural InformationProcessing Systems (NIPS),2006.
[62] R.J. Hanisch, R.L. White, R.L. Gilliland, Deconvolution of images and spectra. AcademicPress, California,1997.
[63] S. Schuon, K. Diepold. Comparison of motion de-blur algorithms and real worlddeployment, Acta Astronautica, pp:1050-1065,2009
[64] D. Krishnan, R. Fergus, Fast Image Deconvolution using Hyper-Laplacian Priors, in: NIPS,2009
[65] N. Joshi, C. Zitnick, R. Szeliski, D. Kriegman, Image deblurring and denoising using colorpriors, In CVPR2009.
[66] A. Levin, R. Fergus, F. Durand, and W. T. Freeman. Image and depth from a conventionalcamera with a coded aperture. ACM Transactions on Graphics,26(31):70:1–70:9,2007.
[67] Y. You and M. Kaveh, Blind Image Restoration by Anisotropic Regularization, IEEETransactions on Image Processing, vol.8, no.3, pp:396-407,1999.
[68] T. F. Chan and C. K. Wong, Total Variation Blind Deconvolution, IEEE Transactions onImage Processing, vol.7, no.3, pp:370-375,1998.
[69] Christian J. Schuler, Harold Christopher Burger, Stefan Harmeling, and Bernhard Schlkopf,“A machine learning approach for non-blind image deconvolution”, CVPR2013
[70] D. Zoran and Y. Weiss. From learning models of natural image patches to whole imagerestoration. In ICCV,2011.
[71] X. Chen, F. Li, J. Yang, J. Yu, A Theoretical Analysis of Camera Response Functions inImage Deblurring, European Conference on Computer Vision, in: ECCV,2012.
[72] S. Kim, H. Lin, Z. Lu, S. Susstrunk, S. Lin, M. S. Brown. A New In-Camera ImagingModel for Color Computer Vision and its Application. IEEE Transactions on Pattern Analysisand Machine Intelligence (TPAMI),34(2), pp.2289-2302,2012
[73] A. Levin, Y. Weiss, F. Durand and W. T. Freeman. Understanding and evaluating blinddeconvolution algorithms, In CVPR2009.
[74] M. Brown and W. Seales, Image restoration of arbitrarily warped documents, IEEETran. PAMI, VOL.26, NO.10, pp:1295-1306,2004
[75] L. Zhang, A. Yip and C. Tan, Removing shading distortions in camera-based documentimages using inpainting and surface fitting with radial basis functions, in ICDAR2007.
[76] L. Likforman-Sulem, J. Darbon and E. Barney Smith, Pre-processing of degraded printeddocuments by non-local means and total variation, in ICDAR2009.
[77] Y. Tian and W. Ming, Adaptive deblurring for camera-based document image processing,Lecture Notes in Computer Science,2009, Volume5876, pp:767-777,2009
[78] L. Kenneth G, Text image deblurring by high-probability word selection, US Patent6282324, Publication Date2001.
[79] X. Qi, L. Zhang, C. Tan, Motion deblurring for optical character recognition, inICDAR2005.
[80] A. Gupta, N. Joshi, C. Zitnick, M. Cohen, B. Curless. Single image deblurring using motiondensity functions. In ECCV2010.
[81] J. Bardsley, S. Jefferies, J. Nagy, and R. Plemmons, Blind iterative restoration of imageswith spatially-varying blur, Opt. Express14, pp:1767–1782,2006
[82] S. Babacan, R. Molina, and A. Katsaggelos, Variational bayesian blind deconvolution usinga total variation prior, IEEE Transactions on Image Processing, Volume18,Issue1,18(1):12-26,2009.
[83] T. Bishop, R. Molina, and J. R. Hopgood, Blind restoration of blurred photographs via ARmodelling and MCMC, in ICIP2008.
[84] T. Kanungo and Q. Zheng, Estimating degradation model parameters using neighborhoodpattern distributions: an optimization approach, IEEE Trans. PAMI. Volume26, Issue4, pp:520-524,2004.
[85] X. Chen, X. He, J. Yang, and Q. Wu. An effective document image deblurring algorithm, In:CVPR,2011
[86] H. Cho and J. Wang and S. Lee, Text Image Deblurring Using Text-Specific Properties,ECCV,2012.
[87] T. Kasar, J. Kumar and A. Ramakrishnan, Font and background color independent textbinarization，In: ICDAR,2007.
[88] J. S. Valverde and R. R. Grigat, Optimum binarization of technical document images, In:ICIP,2000.
[89] F. Drira, F. LeBourgeois, and H. Emptoz，A coupled mean shift-anisotropic diffusionapproach for document image segmentation and restoration, ICDAR, pp:814-818,2007
[90] C. Gopalan and D.Manjula, Sliding window approach based text binarisation from complextextual images, International Journal on Computer Science and Engineering, Vol.02, No.02,pp:309-313,2010
[91] S. Osher, M. Burger, D. Goldfarb, J. Xu, W. Yin, An iterative regularization method fortotal variation-based image restoration, Multiscale Modeling&Simulation, Vol.4, No.2. pp.460-489.2005
[92] R. Jian, et al., Machine vision, MIT Press and McGraw-Hill, Inc,1995.
[93] Krishnan, D., Tay, T., Fergus, R, Blind deconvolution using a normalized sparsity measure.In: CVPR2011
[94] Y. Tai, S. Lin, Motion-aware noise filtering for deblurring of noisy and blurry image, In:CVPR2012.
[95] P. Debevec, J. Malik, Recovering high dynamic range radiance maps from photographs. In:SIGGRAPH,1997
[96] Y. Chang, J. Reid, RGB calibration for color image-analysis in machine vision. IEEE Trans.on IP5:1414-1422,1996
[97] Mitsunaga, T., Nayar, S.K, Radiometric self calibration. In: CVPR (1999)
[98] Grossberg, M.D., Nayar, S.K, Modeling the space of camera response functions. IEEETrans. PAMI (26):1272-1282(2004)
[99] Kim, S.J., Pollefeys, M, Robust radiometric calibration and vignetting correction. IEEETrans. PAMI (30):562-576(2008)
[100] Kim, S., Frahm, J., Pollefeys, M, Radiometric calibration with illumination change foroutdoor scene analysis. In: CVPR (2008)
[101] Lin, S., Gu, J., Yamazaki, S., Shum, H.Y, Radiometric calibration from a single image. In:CVPR (2004)
[102] Lin, S., Zhang, L, Determining the radiometric response function from a single grayscaleimage. In: CVPR (2005)
[103] Y. Matsushita, S. Lin, Radiometric calibration from noise distributions. In: CVPR (2007)
[104] Kim, S., Tai, Y.W., Kim, S., Brown, M.S., Matsushita, Y, Nonlinear camera responsefunctions and image deblurring. In: CVPR (2012)
[105] Lee, J.Y., Shi, B., Matsushita, Y., Kweon, I.S., Ikeuchi, K, Radiometric calibration bytransform invariant low-rank structure. In: CVPR (2011)
[106] B. Wilburn, H. Xu, Y. Matsushita, Radiometric calibration using temporal irradiancemixtures. In: CVPR (2008)
[107] Y. Tai, X. Chen, S. Kim, S. Kim, F. Li, J. Yang, J. Yu, Y. Matsushita, M. Brown,Nonlinear Camera Response Functions and Image Deblurring: Theoretical Analysis and Practice.IEEE Trans Pattern Anal Mach Intell. Feb.35(10):2498-2512,2013.
[108] Farid, H, Blind inverse gamma correction. IEEE Transactions on Image Processing,10:1428-1433(2001)
[109] Ng, T.T., Chang, S.F., Tsui, M.P, Using geometry invariants for camera response functionestimation. In: CVPR (2007)
[110] L. I. Rudin, S. Osher, and E. Fatemi. Nonlinear total variation based noise removalalgorithms. Physica D: Nonlinear Phenomena,60:259–268,1992.
[111] P. Perona and J. Malik. Scale-space and edge detection using anisotropic diffusion. IEEETrans. PAMI.,12(7):629-639,1990.
[112] C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. In ICCV,1998.
[113] J. Portilla, V. Strela, M. J. Wainwright, and E. P. Simoncelli. Image denoising using scalemixtures of Gaussians in the wavelet domain. IEEE Trans. Imag. Proc.,12:1338—1351,2003.
[114] http://www.gris.informatik.tudarmstadt.de/sroth/research/foe.
[115] A. Buades and B. Coll. A non-local algorithm for image denoising. In CVPR,2005.
[116] V. K. Kostadin Dabov, Alessandro Foi and K. Egiazarian. Image denoising withblock-matching and3d filtering. In Proc. SPIE6064,606414(2006), pages454–467.
[117] L. Zhang, W. Dong, D. Zhang, and G. Shi. Two-stage image denoising by principalcomponent analysis with local pixel grouping. Pattern Recogn.,43(4):1531–1549,2010.
[118] A. Adams, N. Gelfand, J. Dolson, and M. Levoy. Gaussian kd-trees for fasthigh-dimensional filtering. ACM Trans.Graph.,28:21:1–21:12,2009.
[119] X. Bai and G. Sapiro. A geodesic framework for fast interactive image and videosegmentation and matting. In ICCV,2007.
[120] P. J. Burt and E. H. Adelson. Readings in computer vision: issues, problems, principles,and paradigms.1987.
[121] Q. Yang, K.-H. Tan, and N. Ahuja. Real-time o(1) bilateral filtering. In CVPR, pages557–564,2009.
[122] Q. Yang. Recursive bilateral filtering. In ECCV,2012.
[123] F. Durand and J. Dorsey. Fast bilateral filtering for the display of high-dynamic-rangeimages, pages:257-266,2002.
[124] A. Criminisi, T. Sharp, C. Rother, and P. P’erez. Geodesic image and video editing. ACMTrans. Graph.,29:790-804,2010.
[125] G. A. Pierre Charbonnier, Laure Blanc-Feraud and M. Barlaud. Deterministicedge-preserving regularization in computed imaging. IEEE Trans. on Imag. Proc.,6(2):298-311,1997
[126] D. Barash. A fundamental relationship between bilateral filtering, adaptive smoothing, andthe nonlinear diffusion equation. IEEE Trans. PAMI.,24(6):844–847,2002.
[127] S. Roth and M. J. Black. Fields of experts: A framework for learning image priors. InCVPR, pages860–867,2005.
[128] Weiss, Y., Freeman,W.T, What makes a good model of natural images? In:CVPR (2007).
[129] S. Paris and F. Durand. A fast approximation of the bilateral filter using a signalprocessing approach. IJCV,81:568--580,2006.
[130] B. Weiss. Fast median and bilateral filtering. ACM Trans. Graph.,25(3):519–526, July2006.
[131] F. Porikli. Constant time O(1) bilateral filtering. In CVPR,2008.
[132] N. Kumar, L. Zhang, and S. Nayar. What is a good nearest neighbors algorithm for findingsimilar patches in images? In ECCV,2008.
[133] T. Brox, O. Kleinschmidt, and D. Cremers. Efficient nonlocal means for denoising oftextural patterns. IEEE Trans. On Imag. Proc.17(7):1083–1092,2008.
[134] K. He and J. Sun. Computing nearest-neighbor fields via propagation-assisted kd-trees. InCVPR,2012.
[135] V. Gulshan, C. Rother, A. Criminisi, A. Blake, and A. Zisserman. Geodesic star convexityfor interactive image segmentation. In CVPR,2010.
[136] A. Criminisi, T. Sharp, and A. Blake. Geos: Geodesic image segmentation. In ECCV,2008.
[137] J. Grazzini and P. Soille. Edge-preserving smoothing using a similarity measure inadaptive geodesic neighbourhoods. Pattern Recogn.,42(10):2306–2316,2009.
[138] L. Yatziv, L. Yatziv, G. Sapiro, and G. Sapiro. Fast image and video colorization usingchrominance blending. IEEE Trans. on Imag. Proc.,15(5):1120-1129,2006.
[139] X. Bai and G. Sapiro. Geodesic matting: A framework for fast interactive image and videosegmentation and matting. Int. J. Comput. Vision,82(2):113–132, Apr.2009.
[140] D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented naturalimages and its application to evaluating segmentation algorithms and measuring ecologicalstatistics. In ICCV,2001.
[141] L. Condat. A Simple Trick to Speed Up and Improve the Non-Local Means, Technicalreport, GREYC laboratory, Centre national de la recherché scientifique (CNRS), France,2010.
[142] A. Foi, V. Katkovnik, and K. Egiazarian. Pointwise shape adaptive dct for high-qualitydenoising and deblocking of grayscale and color images, IEEE Transactions on ImageProcessing,16(5):1395-1411,2007
[143] Markku Makitalo, Alessandro Foi, Optimal Inversion of the Anscombe Transformation inLow-Count Poisson Image Denoising, IEEE Transactions on Image Processing,20(1):99-1092011
[144] Bo Zhang, Mohamed-Jalal Fadili, and Jean-Luc Starck, Wavelets, Ridgelets, andCurvelets for Poisson Noise Removal, IEEE Transactions on Image Processing,17(7):1093-1108,2008
[145] http://www.neatimage.com.
[146] http://www.picturecode.com.