计算机科学 ›› 2018, Vol. 45 ›› Issue (2): 147-151.doi: 10.11896/j.issn.1002-137X.2018.02.026
李键红,吕巨建,吴亚榕
LI Jian-hong, LV Ju-jian and WU Ya-rong
摘要： 图像的自相似性质和图像质量之间存在着密切的关系,清晰的自然图像中几乎所有的图像片都在其自身或较低尺度内存在着重复。然而,在存在噪声或模糊等降质处理的图像中,这一性质明显减弱。针对这一现象,提出一种最大化自相似性先验的盲单帧图像超分辨率算法。该算法通过迭代计算求解超分辨率图像和降质过程的模糊核,使得到的超分辨图像中的任一图像片在输入的低分辨率图像中都以最大的概率存在。这一算法不仅能够准确地计算降质过程的模糊核,得到高质量的高分辨率图像,而且其先验知识随着输入图像的不同而自动进行调整,使得算法具有更强的鲁棒性。大量实验表明,该算法的PSNR,SSIM参数结果较主流算法都有着明显的优势。
| [1] SUN J,SUN J,XU Z B,et al.Image super-resolution using gradient profile prior[C]∥CVPR.2008:1-8. [2] SUN J,SUN J,XU Z B,et al.Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement[J].IEEE Transactions on Image Processing,2011,0(6):1529-1542. [3] WANF Z W,LIU D,YANG J C,et al.Deep Networks for Image Super-Resolution with Sparse Prior[C]∥ICCV.2015:370-378. [4] ROSTAMI M,WANG Z.Image Super-Resolution Based onSparsity Prior via Smoothed l0 Norm [C]∥2011 Symposium Advanced Intelligent Systems.Waterloo,ON,Canada,2011. [5] DONG W S,ZHANG L,SHI G M.Centralized sparse representation for image restoration[C]∥ICCV.2011:1259-1266. [6] ZHANG H C,YANG J C,ZHANG Y N,et al.Non-Local Kernel Regression for Image and Video Restoration[C]∥ECCV.2010:566-579. [7] XU J,ZHANG L,ZUO W M,et al.Patch Group Based Nonlocal Self Similarity Prior Learning for Image Denoising[C]∥ICCV.2015:244-252. [8] EFRAT N,GLASNER D,APARTSIN A,et al.Accurate BlurModels vs.Image Priors in Single Image Super-resolution[C]∥ICCV.2013:2832-2839. [9] MUDENAGUDI U,SINGULAR R,KALRA P.Super Resolution Using Graph Cut[C]∥ACCV.2006:385-394. [10] YANG J C,WRIGHT J,HUANG T S,et al.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19(11):2861-2873. [11] DONG C,CHEN C L,HE K M,et al.Learning a Deep Convolutional Network for Image Super-Resolution[C]∥ECCV.2014:184-199. [12] GLASNER D,BAGON S,IRANI M.Super-resolution from a single image[C]∥ ICCV.2009:349-356. [13] ZEYDE R,ELAD M,PROTTER M.On Single Image Scale-Up Using Sparse Representations[C]∥ICCS.2012:711-730. [14] TIMOFTE R,DE V,GOOL L V.Anchored Neighborhood Regression for Fast Example-Based Super-Resolution[C]∥ICCV.2013:1920-1927. [15] FATTAL R.Image upsampling via imposed edge statistics[C]∥ACM Transactions on Graphics.2007:95. [16] JOSHI N,SZELISKI R,KRIEGMAN D J.PSF estimation using sharp edge prediction[C]∥CVPR.2008:1-8. [17] MICHAELI T,IRANI M.Nonparametric Blind Super-resolution[C]∥ICCV.2013:945-952. [18] KWON Y,KIM K I,TOMPKIN J,et al.Efficient Learning of Image Super-Resolution and Compression Artifact Removal with Semi-Local Gaussian Processes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,7(9):1792-1805. [19] FERGUS R,SINGH B,HERTZMANN A,et al.Removing ca-mera shake from a single photograph[J].ACM Transactions on Graphics,2006,25(3):787-794. [20] BAKER S,KANADE T.Limits on super-resolution and how to break them[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,4(9):1167-1183. [21] ZONTAK M,MOSSERI I,IRANI M.Separating signal fromnoise using patch recurrence across scales[C]∥CVPR.2013:1195-1202. [22] MICHAELI T,IRANI M.Blind Deblurring Using InternalPatch Recurrence [C]∥ECCV.2014:783-798. [23] HARMELING S,SRA S,HIRSCH M,et al.Multiframe blind deconvolution,super-resolution,and saturation correction via incremental EM[C]∥ICIP.2010:3313-3316. [24] LEVIN A,WEISS Y,DURAND F,et al.Understanding andevaluating blind deconvolution algorithms[C]∥CVPR.2009:1964-1971. [25] ZORAN D,WEISS Y.From learning models of natural image patches to whole image restoration[C]∥ICCV.2011:479-486. [26] WANG Y,YANG J,YIN W,et al.A New Alternating Minimization Algorithm for Total Variation Image Reconstruction[J].Siam Journal on Imaging Sciences,2008,1(3):248-272. [27] KOMODAKIS N,PARAGIONS N.MRF-Based blind image de-convolution[J].Lecture Notes in Computer Science,2012,6:361-374. [28] LI J H,WU Y R,LUO X N.Single Image Super-ResolutionUsing Maximizing Self-Similarity Prior[J].Mathematical Problems in Engineering,2016,2015(510):1-10. [29] YANG J C,WRIGHT J,HUANG T,et al.Image super-resolution as sparse representation of raw image patches[C]∥CVPR.2008:1-8. [30] TIMOFTE R,SMET V D,GOOL L V.A+:Adjusted Anchored Neighborhood Regression for Fast Super-Resolution[C]∥ACCV.2014:111-126. [31] YANG M C,WANG Y C F.A Self-Learning Approach to Single Image Super-Resolution[J].IEEE Transactions on Multimedia,2013,5(3):498-508. |
| No related articles found! |
|
||
首页