空间尺度信息的运动模糊核估计方法
作者:
作者简介:

唐述(1981-),男,重庆人,博士,副教授,CCF专业会员,主要研究领域为图像处理,信息获取与处理;万盛道(1995-),男,硕士生,主要研究领域为模糊图像复原,深度学习,神经网络;杨书丽(1995-),女,硕士生,主要研究领域为图像超分辨率重建,深度学习,神经网络;谢显中(1965-),男,博士,教授,博士生导师,CCF高级会员,主要研究领域为感知无线电,协作通信,MIMO预编码;夏明(1989-),男,硕士生,主要研究领域为图像编码,压缩感知;张旭(1981-),男,博士,副教授,CCF专业会员,主要研究领域为大规模数据智能处理与分析.

通讯作者:

唐述,E-mail:tangshu@cqupt.edu.cn

中图分类号:

TP391

基金项目:

国家自然科学基金(61601070,61271259);重庆市教委科学技术研究计划(KJZD-K201800603,KJZD-M201900602);重庆市基础与前沿研究计划(CSTC2016jcyjA0455,CSTC2014kjrc-qnrc40002);重庆市教委科学技术研究项目(KJ1600411,KJ14004 29)


Spatial-scale-information Method for Motion Blur Kernel Estimation
Author:
Fund Project:

National Natural Science Foundation of China (61601070, 61271259); Project of Science and Technology Research of Chongqing Education Commission (KJZD-K201800603, KJZD-M201900602); Fundamental and Advanced Technology Research Project of Chongqing (CSTC2016jcyjA0455, CSTC2014kjrc-qnrc40002); Science and Technology Research Project of Chongqing Municipal Education Commission (KJ1600411, KJ1400429)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [18]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    运动模糊核的准确估计是实现单幅运动模糊图像盲复原成功的关键.但是,因为不能准确提取出有利的图像边缘以及简单的正则化约束项的设计,导致现有运动模糊核(motion blur kernel,简称MBK)的估计并不十分准确,存在瑕疵.因此,为了能够估计出准确的运动模糊核,提出了一种基于空间尺度信息的运动模糊核估计方法.首先,为了准确地提取有利的图像边缘,移除有害的图像结构,提出了一种基于图像空间尺度信息的图像平滑模型,实现有利图像边缘的准确快速提取;然后,从运动模糊核的内在特性出发,将空间域的L0范数和梯度域的L2范数结合到一起,提出了一种正则化约束模型,很好地保证了运动模糊核的稀疏平滑特性,并结合之前提取出的有利的图像边缘,共同实现运动模糊核的准确估计;最后,采用一种半二次性分裂的交互式最优化策略对提出的模型进行最优化求解.在客观的评价指标和主观的视觉效果上进行了大量实验,其结果证明所提出的方法能够估计出更准确的MBK和复原出更高质量的去模糊图像.

    Abstract:

    The accurate motion blur kernel (MBK) estimation is the key for the success of the single-image blind motion deblurring. Nevertheless, because of the imperfect useful edges selection and the simple regularizers design, the MBKs estimated by existing methods are inaccurate and contain various flaws. Therefore, in order to estimate an accurate MBK, in this study, a spatial-scale-information method for MBK estimation is proposed. First, in order to accurately extract the useful image edges and remove the pernicious image structures, an image smoothing model based on the spatial scale information is proposed, such that the useful image edges can be extracted accurately and quickly. Then, according to the characteristics of the MBK, a regularization constraint model, which combines spatial L0 norm with gradient L2 norm, is proposed for preserving the continuity and the sparsity of the MBK well. By combining the extracted useful image edges and the proposed regularization constraint model, the accurate MBK estimation can be achieved. Finally, a half-quadratic splitting alternating optimization strategy is employed to solve the proposed model. Extensive experiments results demonstrate that the proposed method can estimate more accurate MBKs and obtain higher quality deblurring images in terms of both quantitative metrics and subjective vision.

    参考文献
    [1] Shan Q, Jia J, Agarwala A. High-Quality motion deblurring from a single image. ACM Trans. on Graphics, 2008,27(3):Article No. 73.
    [2] Cho S, Lee S. Fast motion deblurring. ACM Trans. on Graphics, 2009,28(5):Article No.145.
    [3] Krishnan D, Tay T, Fergus R. Blind deconvolution using a normalized sparsity measure. In:Proc. of the IEEE Computer Vision and Pattern Recognition (CVPR). Providence:IEEE, 2011. 233-240.[doi:10.1109/CVPR.2011.5995521]
    [4] Li WH, Li QL, Gong WG, Tang S. Total variation blind deconvolution employing split Bregman iteration. ELSEVIER Journal of Visual Communication and Image Representation, 2012,23(3):409-417.
    [5] Xu L, Jia J. Two-Phase kernel estimation for robust motion deblurring. In:Daniilidis K, Maragos P, Paragios N, eds. Proc. of the 11th European Conf. on Computer Vision (ECCV). Part I. LNCS 6311, Berlin, Heidelberg:Springer-Verlag, 2010. 157-170.
    [6] Xu L, Zheng SC, Jia J. Unnatural L0 sparse representation for natural image deblurring. In:Proc. of the IEEE Conf. on Computer Society Vision and Pattern Recognition (CVPR). Portland:IEEE, 2013. 1107-1114.[doi:10.1109/CVPR.2013.147]
    [7] Pan JS, Liu RS, Su ZX, Gu XF. Kernel estimation from salient structure for robust motion deblurring. ELSEVIER Signal Processing:Image Communication, 2013,28:1156-1170.
    [8] Pan J, Sun D, Pfister H, and Yang MH. Blind image deblurring using dark channel prior. In:Proc. of the IEEE Conf. on Computer Society Vision and Pattern Recognition (CVPR). Las Vegas:IEEE, 2016. 1628-1636.[doi:10.1109/CVPR.2016.180]
    [9] Ma ZY, Liao RJ, Tao X, Xu L, Jia J, Wu EH. Handling motion blur in multi-frame super-resolution. In:Proc. of the IEEE Conf. on Computer Society Vision and Pattern Recognition (CVPR). Boston:IEEE. 2015. 5224-5232.[doi:10.1109/CVPR.2015.7299159]
    [10] Perrone D, Diethelm R, Favaro P. Blind deconvolution via lower-bounded logarithmic image priors. In:Tai XC, et al., eds. Proc. of the Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR). LNCS 8932, Springer Int'l Publishing, 2015. 112-125.
    [11] Zuo WM, Ren DW, Zhang D, Gu SH, Zhang L. Learning iteration-wise generalized shrinkage-thresholding operators for blind deconvolution. IEEE Trans. on Image Processing, 2016,25(4):1751-1764.
    [12] Pan JS, Hu Z, Su ZX, Yang MH. L0-Regularized intensity and gradient prior for deblurring text images and beyond. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2017,39(2):342-355.
    [13] Cai JF, Ji H, Liu CQ, Shen ZW. Framelet-Based blind motion deblurring from a single image. IEEE Trans. on Image Processing, 2012,21(2):562-572.
    [14] Krishnan D, Fergus R. Fast image deconvolution using hyper-laplacian priors. In:Proc. of the Advances in Neural Information Processing Systems. 2009. 1033-1041.
    [15] Xu L, Yan Q, Xia Y, Jia J. Structure extraction from texture via relative total variation. ACM Trans. on Graphics, 2012,31(6):139:1-139:10.
    [16] Xu L, Lu CW, Xu Y, Jia JY. Image smoothing via L0 gradient minimization. ACM Trans. on Graphics, 2011,30(6):174:1-174:12.
    [17] Sun L, Cho S, Wang J, Hays J. Edge-Based blur kernel estimation using patch priors. In:Proc. of the IEEE Int'l Conf. on Computational Photography (ICCP). Cambridge:IEEE. 2013. 1-8.[doi:10.1109/ICCPhot.2013.6528301]
    [18] Ghadiyaram D, Bovik AC. Perceptual quality prediction on authentically distorted images using a bag of features approach. Journal of Vision, 2017,17(1):Article No.32.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

唐述,万盛道,杨书丽,谢显中,夏明,张旭.空间尺度信息的运动模糊核估计方法.软件学报,2019,30(12):3876-3891

复制
分享
文章指标
  • 点击次数:1440
  • 下载次数: 3323
  • HTML阅读次数: 2016
  • 引用次数: 0
历史
  • 收稿日期:2017-04-19
  • 最后修改日期:2018-01-26
  • 在线发布日期: 2019-12-05
文章二维码
您是第19791963位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号