首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221011--1)

密集连接的生成对抗网络图像超分辨率重建

Super-Resolution Reconstruction of Densely Connected Generative Adversarial Network Images

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

摘要

针对图像超分辨率重建过程中出现的边缘细节模糊、图像特征丢失的问题,提出基于密集连接的生成对抗网络图像超分辨率重建算法。该算法由生成网络和判别网络组成,在生成网络结构中,将原始低分辨率图像作为网络的输入,为了实现对特征的充分利用,采用密集连接方式将浅层网络的特征输送到深层网络结构的每一层,有效避免图像特征的丢失。并在末端进行亚像素卷积,对图像进行反卷积操作,完成图像最终的超分辨率重建,大大减少了训练耗时。在判别网络结构中,采用6个卷积模块和一个全连接层对真伪图像进行甄别,采用对抗博弈的思想,提升重建图像的质量。实验结果表明,本文算法在视觉效果评估、峰值信噪比值、结构相似性值以及耗时等多方面指标上都有了很大的改善,恢复出较为丰富的图像细节信息,取得了较好的视觉效果和综合特性。

Abstract

Aiming at the problems of blurred edge details and loss of image features in the process of image super-resolution reconstruction, a super-resolution reconstruction algorithm based on dense connection generative adversarial network is proposed. This algorithm consists of a generative network and a discriminative network. In the generative network structure, the original low-resolution image is used as the input of the network. In order to make full use of the features, the features of the shallow network are transferred to each layer of the deep network structure using dense connection, so as to effectively avoid the loss of image features. Sub-pixel convolution is performed at the end, and the image is deconvolved to complete the final super-resolution reconstruction of the image, which greatly reduces the training time. In the discriminative network structure, 6 convolutional modules and a fully connected layer are used to identify true and false images, and the idea of adversarial games is used to improve the quality of reconstructed images. Experimental results show that the proposed algorithm has greatly improved the visual effect assessment, peak signal to noise ratio value, structural similarity value, time-consuming, and indicators. It has restored richer image detail information and achieved better visual effects and comprehensive characteristic.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.221011

所属栏目:图像处理

基金项目:安徽省高等学校省级质量工程: 计算机类专业数学教学创新团队;

收稿日期:2020-02-14

修改稿日期:2020-03-26

网络出版日期:2020-11-01

作者单位    点击查看

李斌:宿州职业技术学院基础教学部, 安徽 宿州 234099
马璐:宿州职业技术学院计算机信息系, 安徽 宿州 234099

联系人作者:李斌(747952996@qq.com)

备注:安徽省高等学校省级质量工程: 计算机类专业数学教学创新团队;

【1】Shi Z T, Wang Z R, Wang R, et al. Single image super-resolution based on convolutional neural network [J]. Laser & Optoelectronics Progress. 2018, 55(12): 121001.
史紫腾, 王知人, 王瑞, 等. 基于卷积神经网络的单幅图像超分辨 [J]. 激光与光电子学进展. 2018, 55(12): 121001.

【2】Zhang L, Wu X L. An edge-guided image interpolation algorithm via directional filtering and data fusion [J]. IEEE Transactions on Image Processing. 2006, 15(8): 2226-2238.

【3】Dai S Y, Han M, Xu W, et al. SoftCuts: a soft edge smoothness prior for color image super-resolution [J]. IEEE Transactions on Image Processing. 2009, 18(5): 969-981.

【4】Hu S Y, Wang G D, Zhao Y, et al. Image super-resolution network based on dense connection and squeeze module [J]. Laser & Optoelectronics Progress. 2019, 56(20): 201005.
胡诗语, 王国栋, 赵毅, 等. 基于密集连接与激励模块的图像超分辨网络 [J]. 激光与光电子学进展. 2019, 56(20): 201005.

【5】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.

【6】Timofte R, De V, Van L. Anchored neighborhood regression for fast example-based super-resolution[C]//2013 IEEE International Conference on Computer Vision, December 1-8, 2013, Sydney, NSW, Australia. New York: , 2013, 1920-1927.

【7】Timofte R, de Smet V, van Gool L. A+: adjusted anchored neighborhood regression for fast super-resolution[M]. //Computer Vision-ACCV 2014. Cham: , 2015, 111-126.

【8】Dong C, Loy C C, He K M, et al. Learning a deep convolutional network for image super-resolution [J]. Computer Vision-ECCV 2014. 2014, 8692: 184-199.

【9】Dong C, Loy C C, He K M, et al. Image super-resolution using deep convolutional networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016, 38(2): 295-307.

【10】Wang Z W, Liu D, Yang J C, et al. Deep networks for image super-resolution with sparse prior[C]//2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: , 2015, 370-378.

【11】Shi W Z, Caballero J, Huszár F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network . [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, 1874-1883.

【12】Kim J, Lee J K, Lee K M. Accurate image super-resolution using very deep convolutional networks . [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, 1646-1654.

【13】Kim J, Lee J K, Lee K M. Deeply-recursive convolutional network for image super-resolution . [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, 1637-1645.

【14】Goodfellow I J, Pouget-Abadie J, Mirza M, et al. -06-10)[2020-02-14] . 2014, org/abs/1406: 2661.Goodfellow I J, Pouget-Abadie J, Mirza M, et al. -06-10)[2020-02-14] . 2014, org/abs/1406: 2661.

【15】Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network . [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017, 105-114.

【16】Zhao L J, Bai H H, Liang J, et al. Simultaneous color-depth super-resolution with conditional generative adversarial networks [J]. Pattern Recognition. 2019, 88: 356-369.

【17】Yang X L, Lin S Z, Lu X F, et al. Multimodal image fusion based on generative adversarial networks [J]. Laser & Optoelectronics Progress. 2019, 56(16): 161004.
杨晓莉, 蔺素珍, 禄晓飞, 等. 基于生成对抗网络的多模态图像融合 [J]. 激光与光电子学进展. 2019, 56(16): 161004.

【18】Huang G, Liu Z, van der Maaten L, et al. -01-28)[2020-02-14] . 2018, org/abs/1608: 06993.Huang G, Liu Z, van der Maaten L, et al. -01-28)[2020-02-14] . 2018, org/abs/1608: 06993.

【19】Huang K B, Hu R M, Jiang J J, et al. Face image super-resolution through improved neighbor embedding[M]. //Multimedia Modeling: , 2016, 409-420.

【20】Martin D, Fowlkes C, Tal D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics [J]. Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001. 2001, 2: 416-423.

【21】Huang J B, Singh A, Ahuja N. Single image super-resolution from transformed self-exemplars[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: , 2015, 5197-5206.

【22】Tai Y, Yang J, Liu X M. Image super-resolution via deep recursive residual network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: , 2017, 2790-2798.

【23】de Boor C. Bicubic spline interpolation [J]. Journal of Mathematics & Physics. 1962, 41(1): 212-218.

引用该论文

Li Bin,Ma Lu. Super-Resolution Reconstruction of Densely Connected Generative Adversarial Network Images[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221011

李斌,马璐. 密集连接的生成对抗网络图像超分辨率重建[J]. 激光与光电子学进展, 2020, 57(22): 221011

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