计算机科学 ›› 2018, Vol. 45 ›› Issue (3): 263-267.doi: 10.11896/j.issn.1002-137X.2018.03.042
陈诚,常侃,莫彩网,李天亦,覃团发
CHEN Cheng, CHANG Kan, MO Cai-wang, LI Tian-yi and QIN Tuan-fa
摘要: 传统的基于重建的单视频超分辨率方法能够获得较好的重建效果。然而,已有算法没有充分利用视频内的帧间、帧内相关性,重建效果仍有待提升。针对这一问题,提出了一种新的单视频超分辨率算法。为充分利用帧内相关性,采用非局部均值模型表征帧内非局部结构特性,采用总变分模型表征帧内局部结构特性;为了探索帧间相关性,采用光流法进行帧间预测。最后,为了求解所建立的优化问题,提出了基于split-Bregman方法的快速迭代算法。实验结果表明,与同类算法相比,所提算法在主、客观质量上均有相应的提升。
[1] XU Y M,SONG J W,XIAO X J.Super resolution algorithm based on sub-pixel block matching and dictionary learning[J].Computer Science,2016,3(8):304-308.(in Chinese) 徐煜明,宋佳伟,肖贤建.基于亚像素块匹配和字典学习的超分辨率算法[J].计算机科学,2016,3(8):304-308. [2] HUNG E M,GARCIA D C,DE QUEIROZ R L.Example-based enhancement of degraded video[J].IEEE Signal Processing Letters,2014,21(9):1140-1144. [3] HUNG E M,DE QUEIROZ R L,BRANDI F,et al.Video super-resolution using codebooks derived From key-Frames[J].IEEE Transactions on Circuits and Systems for Video Technology,2012,9(22):1321-1331. [4] LI L H,DU J P,LIANG M Y,et al.Video super-resolution algorithm based on spatial-temporal feature and neural network[J].Journal of Beijing University of Posts and Telecommunications,2016,39(4):1-6.(in Chinese) 李玲慧,杜军平,梁美玉,等.基于时空特征和神经网络的视频超分辨率算法[J].北京邮电大学学报,2016,39(4):1-6. [5] LEDIG C,THEIS L,HUSZR F,et al.Photo-realistic singleimage super-resolution using a generative adversarial network[J].arXiv preprint arXiv:1609.04802,2016. [6] RUDIN L I,OSHER S,FATEMI E.Nonlinear total variation based noise removal algorithms[J].Physica D:Nonlinear Phenomena,1992,60(1):259-268. [7] LI C,YIN W,JIANG H,et al.An efficient augmented Lagran-gian method with applications to total variation minimization[J].Computational Optimization and Applications,2013,56(3):507-530. [8] FARSIU S,ROBINSON M D,ELAD M,et al.Fast and robust multiframe super resolution[J].IEEE Transactions on Image Processing,2004,13(10):1327-1344. [9] YUAN Q,ZHANG L,SHEN H.Regional spatially adaptive total variation super-resolution with spatial information filtering and clustering[J].IEEE Transactions on Image Processing,2013,22(6):2327-2342. [10] BELEKOS S P,GALATSANOS N P,KATSAGGELOS A K.Maximum a posteriori video super-resolution using a new multichannel image prior[J].IEEE Transactions on Image Proces-sing,2010,19(6):1451-1464. [11] ZHANG Y L,GAN Z L,ZHU X C.Video super-resolutionmethod based on similarity constraints[J].Journal of Image and Graphics,2013,18(7):761-767.(in Chinese) 张义轮,干宗良,朱秀昌.相似性约束的视频超分辨率重建[J].中国图象图形学报,2013,18(7):761-767. [12] ZHU Y,LI K,JIANG J.Video super-resolution based on automatic key-frame selection and feature-guided variational optical flow[J].Signal Processing:Image Communication,2014,29(8):875-886. [13] LI K,ZHU Y,YANG J,et al.Video super-resolution using anadaptive superpixel-guided auto-regressive model[J].Pattern Recognition,2016,51(C):59-71. [14] LU S,OSHER S J.Decomposition of images by the ani-sotropic Rudin-Osher-Fatemimodel[J].Communications on Pure and Applied Mathematics,2004,57(12):1609-1626. [15] BUADES A,COLL B,MOREL J M.A non-local algorithm for image denoising[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005(CVPR 2005).IEEE,2005:60-65. [16] SONG B C,JEONG S C,CHOI Y.Video super-resolution algorithm using bi-directional overlapped block motion compensation and on-the-fly dictionary training[J].IEEE Transactions on Circuits and Systems for Video Technology,2011,21(3):274-285. [17] KIM K I,KWON Y.Single-image super-resolution using sparse regression and natural image prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(6):1127-1133. [18] BRANDI F,QUEIROZ R,MUKHERJEE D.Super-resolution of video using key frames and motion estimation[C]∥2008 15th IEEE International Conference on Image Processing.IEEE,2008:321-324. [19] GOLDSTEIN T,OSHER S.The split Bregman method for L1-regularized problems[J].SIAM Journal on Imaging Sciences,2009,2(2):323-343. |
No related articles found! |
|