首页 > 论文 > 光学学报 > 38卷 > 10期(pp:1010003--1)

联合深度去噪先验图像盲去模糊

Joint Deep Denoising Prior for Image Blind Deblurring

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

目前,基于统计先验的图像去模糊方法对噪声敏感,细节恢复能力有限,而基于先验学习的算法对图像及其模糊类型、噪声水平等适应性较差。针对上述问题,基于图像模糊前后像素直方图统计,首先提出一种简单有效的低值像素先验。然后针对现有方法对图像去模糊后出现大量噪声或伪影等问题,设计深度卷积神经网络学习图像深度去噪先验,并联合低值像素先验、梯度稀疏先验提出新的去模糊模型。同时,在模糊核估计过程中,利用图像分解方法分离出图像的结构层,并在结构层估计模糊核,获得更为准确的估计结果。大量实验结果表明,本文算法不仅具有很好的细节恢复能力,且对图像及其模糊类型、噪声水平等更具稳健性。与现有主流算法相比,本文方法优势明显。

Abstract

The traditional blind image deblurring algorithm based on the statistical prior models has the disadvantages of sensitivity to noise and limited detail recovery, while the learning-based image deblurring algorithm has poor adaptability for blurring kernel and noise level. To address the above problems, we propose a simple and effective low pixel sparse prior based on the statistical differences between the histograms of original and blurred images first. Then, in order to remove the noises and artifacts in restored image, a deep convolution neural network is designed to learn image denoising prior, which combines low pixel sparse prior and gradient sparse prior to form a new image deblurring model. Meanwhile, we estimate the blurring kernel in the structure layer so as to get a more accurate one, and the structure layer can be obtained by the image decomposition method. Numerous experimental results show that the proposed algorithm can restore more image details, and show more robustness to image type, blurring kernel type and noise level. The proposed method outperforms other recent state-of-the-art related approaches.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/aos201838.1010003

所属栏目:图像处理

基金项目:国家自然科学基金(61472274,61632018)

收稿日期:2018-03-19

修改稿日期:2018-05-12

网络出版日期:2018-05-21

作者单位    点击查看

杨爱萍:天津大学电气自动化与信息工程学院, 天津 300072
王金斌:天津大学电气自动化与信息工程学院, 天津 300072
杨炳旺:天津大学电气自动化与信息工程学院, 天津 300072
何宇清:天津大学电气自动化与信息工程学院, 天津 300072

联系人作者:杨爱萍(yangaiping@tju.edu.cn)

【1】Fergus R, Singh B, Hertzmann A, et al. Removing camera shake from a single photograph[J]. ACM Transactions on Graphics, 2006, 25(3): 787-794.

【2】Kotera J, roubek F, Milanfar P. Blind deconvolution using alternating maximum a posteriori estimation with heavy-tailed priors[C]∥International Conference on Computer Analysis of Images and Patterns, 2013: 59-66.

【3】Krishnan D, Tay T, Fergus R. Blind deconvolution using a normalized sparsity measure[C]∥2011 IEEE Conference on Computer Vision and Pattern Recognition, 2011: 233-240.

【4】Xu L, Zheng S, Jia J. Unnatural l0 sparse representation for natural image deblurring[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013: 1107-1114.

【5】Michaeli T, Irani M. Blind deblurring using internal patch recurrence[C]∥European Conference on Computer Vision, 2014: 783-798.

【6】Pan J S, Hu Z, Su Z X, et al. L0-regularized intensity and gradient prior for deblurring text images and beyond[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(2): 342-355.

【7】Shan Q, Jia J Y, Agarwala A. High-quality motion deblurring from a single image[J]. ACM Transactions on Graphics, 2008, 27(3): 73.

【8】Krishnan D, Fergus R. Fast image deconvolution using hyper-Laplacian priors[J]. Advances in Neural Information Processing Systems, 2009: 1033-1041.

【9】Yang A P, Zhang Y, Wang J B, et al. Adaptive weighted generalized total variation image deblurring based on primal-dual algorithm[J]. Laser & Optoelectronics Progress, 2018, 55(4): 041003.
杨爱萍, 张越, 王金斌, 等. 基于原始-对偶算法的自适应加权广义全变差图像去模糊[J]. 激光与光电子学进展, 2018, 55(4): 041003.

【10】Su C, Fu T J, Zhang X X, et al. Adaptively-weighted blind image restoration algorithm based on energy constraint[J]. Acta Optica Sinica, 2018, 38(2): 0210001.
苏畅, 付天骄, 张星祥, 等. 基于能量约束的自适应加权图像盲复原算法[J]. 光学学报, 2018, 38(2): 0210001.

【11】Schuler C J, Hirsch M, Harmeling S, et al. Learning to deblur[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence, 2016, 38(7): 1439-1451.

【12】Xu L, Ren J S J, Liu C, et al. Deep convolutional neural network for image deconvolution[C]∥Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014: 1790-1798.

【13】Su S, Delbracio M, Wang J, et al. Deep video deblurring for hand-held cameras[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1279-1288.

【14】Kim Y, Jung H, Min D, et al. Deeply aggregated alternating minimization for image restoration[C]∥IEEE International Conference on Computer Vision and Pattern Recognition, 2017: 284-292.

【15】Nah S, Kim T H, Lee K M. Deep multi-scale convolutional neural network for dynamic scene deblurring[C]∥Conference on Computer Vision and Pattern Recognition, 2017: 3883-3891.

【16】Pan J, Sun D, Pfister H, et al. Deblurring images via dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017: 1.

【17】Fu X, Lin Q, Guo W, et al. Single image dehaze under non-uniform illumination using bright channel prior[J]. Journal of Theoretical & Applied Information Technology, 2013, 48(3): 1843-1848.

【18】Yan Y, Ren W, Guo Y, et al. Image deblurring via extreme channels prior[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4003-4011.

【19】Zhang K, Zuo W M, Chen Y J, et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155.

【20】Fu X Y, Huang J B, Ding X H, et al. Clearing the skies: a deep network architecture for single-image rain removal[J]. IEEE Transactions on Image Processing, 2017, 26(6): 2944-2956.

【21】Ren W, Liu S, Zhang H, et al. Single image dehazing via multi-scale convolutional neural networks[C]∥European Conference on Computer Vision, 2016: 154-169.

【22】Cai B L, Xu X M, Jia K, et al. DehazeNet: an end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198.

【23】Zhu C, Zhou Y, Xie Z. A pixel-to-pixel convolutional neural network for single image dehazing[C]∥International Conference on Neural Information Processing, 2017: 270-279.

【24】Wang Z, Liu D, Yang J, et al. Deep networks for image super-resolution with sparse prior[C]∥Proceedings of the IEEE International Conference on Computer Vision, 2015: 370-378.

【25】Zhong L, Cho S, Metaxas D, et al. Handling noise in single image deblurring using directional filters[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013: 612-619.

【26】Kingma D P, Ba J. Adam: a method for stochastic optimization[C]∥Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), 2015.

【27】Zhang K, Zuo W, Gu S, et al. Learning deep CNN denoiser prior for image restoration[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2808-2817.

【28】Ulyanov D, Vedaldi A, Lempitsky V. Deep image prior[J]. arXiv, 2017: 1711.10925.

【29】Pan J S, Liu R S, Su Z X, et al. Kernel estimation from salient structure for robust motion deblurring[J]. Signal Processing: Image Communication, 2013, 28(9): 1156-1170.

【30】Li Y, Guo F, Tan R T, et al. A contrast enhancement framework with JPEG artifacts suppression[C]∥European Conference on Computer Vision, 2014: 174-188.

【31】Xu L, Yan Q, Xia Y, et al. Structure extraction from texture via relative total variation[J]. ACM Transactions on Graphics, 2012, 31(6): 139.

【32】Cho S, Lee S. Fast motion deblurring[J]. ACM Transactions on Graphics, 2009, 28(5): 1-8.

【33】Dong J X, Pan J S, Su Z X. Blur kernel estimation via salient edges and low rank prior for blind image deblurring[J]. Signal Processing: Image Communication, 2017, 58: 134-145.

【34】Levin A, Weiss Y, Durand F, et al. Efficient marginal likelihood optimization in blind deconvolution[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2011:2657-2664.

【35】Levin A, Weiss Y, Durand F, et al. Understanding blind deconvolution algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2354-2367.

引用该论文

Yang Aiping,Wang Jinbin,Yang Bingwang,He Yuqing. Joint Deep Denoising Prior for Image Blind Deblurring[J]. Acta Optica Sinica, 2018, 38(10): 1010003

杨爱萍,王金斌,杨炳旺,何宇清. 联合深度去噪先验图像盲去模糊[J]. 光学学报, 2018, 38(10): 1010003

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF