期刊文献+

图像超分辨率重建研究综述 被引量:30

A Survey of Image Super-Resolution Reconstruction
下载PDF
导出
摘要 图像超分辨率重建(Super-resolution Reconstruction,SR)是由一张或多张低分辨率图像得到高分辨率图像的过程.近年来,SR技术不断发展,在许多领域被广泛应用.本文在回顾SR技术发展历史的基础上,全面综述了SR技术在各个时期的代表性方法,重点介绍了基于深度学习的图像超分辨率工作.我们从模型类型、网络结构、信息传递方式等方面对各种算法进行了详细评述,并对比了其优缺点.最后探讨了图像超分辨率技术未来的发展方向. Image super-resolution reconstruction(SR)aims to obtain high-resolution images from one or more low-resolution images.Recently,SR has been developing and widely applied in different fields.This survey retrospects the history of SR technique and provides a comprehensive overview of representative SR methods,with an emphasis on recent deep learning-based approaches.We elaborate the details of various deep learning-based SR methods,including their strengths and weakness,in terms of the deep learning model,architecture,and message pass.Finally,we discuss the possible research directions on SR technique.
作者 唐艳秋 潘泓 朱亚平 李新德 TANG Yan-qiu;PAN Hong;ZHU Ya-ping;LI Xin-de(School of Automation,Southeast University,Nanjing,Jiangsu 210096,China;School of Information and Communication Engineering,Communication University of China,Beijing 100024,China)
出处 《电子学报》 EI CAS CSCD 北大核心 2020年第7期1407-1420,共14页 Acta Electronica Sinica
基金 国家自然科学基金(No.61671151,No.61573097,No.91748106) 江苏省自然科学基金(No.BK20181265) 流程工业综合自动化国家重点实验室基金(No.PAL-N201704) 中国传媒大学优秀博导组项目(No.CUC2019A009) 中国传媒大学重大攻关培育项目-媒介事件中的AI新闻生产系统与关键技术(No.CUC19ZD003)。
关键词 图像超分辨率 深度学习 图像处理 方法综述 image super-resolution reconstruction deep learning image processing methods review
  • 相关文献

参考文献5

二级参考文献32

  • 1韩玉兵,陈小蔷,吴乐南.一种视频序列的超分辨率重建算法[J].电子学报,2005,33(1):126-130. 被引量:8
  • 2Irani M, Peleg S. Improving resolution by image registra- tion[J]. CVGIP:Graphical Models and Image Processing, 1991,53 (3) :231 - 239. 被引量:1
  • 3Stark H, Oskoui P. High-resolution image recovery from image plane arrays using convex projections[ J]. Journal of the Optical Society of America A:Optics, Image Science and Vision, 1989,6 ( 11 ) : 1715 - 1726. 被引量:1
  • 4Freeman T, Jones T R, Pasztor E. Example based superres- olution [ J ]. IEEE Computer 2002,22(2) :56 -65. 被引量:1
  • 5Chang H, Yeung D, Xiong Graphics and Applications, Y. Super-resolution through neighbor embedding [ A ]. IEEE International Conference on Computer Vision and Pattern Recognition [ C ]. Wash- ington, DC, USA : IEEE,2004. 275 - 282. 被引量:1
  • 6Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcomplete dictionaries for sparse represen- tation [ J]. IEEE Trans Signal Process ,2006,54( 11 ) :4311 - 4322. 被引量:1
  • 7Yang J, Wright J, Huang T, et al. Image super-resolution via sparse representation [ J ]. IEEE Transactions on Image Processing ,2010,19 ( 11 ) :2861 - 2873. 被引量:1
  • 8Zeyde R, Elad M, Protter M. On single image scale-up m u- sing sparse representations [ A]. Proceedings of the 7th In- ternational Conference on Curves and Surfaces [ C ]. Avi- gnon, France : Springer, 2012. 6920 : 711 - 730. 被引量:1
  • 9Dong W,Zhang L, Shi G, et al. Image deblurring and su- per-resolution by adaptive sparse domain selection and a- daptive regularization[ J]. Image Processing, IEEE Trans- actions on,2011,20 (7) : 1838 - 1857. 被引量:1
  • 10Wang S, Zhang L, Liang Y, et al. Semi-coupled dictionary learning with applications to image super -resolution and photo-sketch synthesis [ A ]. IEEE International Confer- ence on Computer Vision and Pattern Recognition [ C ]. Providence, RI, USA: IEEE,2012. 2216 - 2223. 被引量:1

共引文献266

同被引文献141

引证文献30

二级引证文献71

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部