Super-resolution reconstruction using nonlocal means

JIA Ping; LI Jia-de; ZHANG Ye

doi:10.3788/OPE.20132106.1576

您当前的位置：

首页 >

文章列表页 >

Super-resolution reconstruction using nonlocal means

更新时间：2020-08-12

- Super-resolution reconstruction using nonlocal means
- Optics and Precision Engineering Vol. 21, Issue 6, Pages: 1576-1585(2013)
- 作者机构：
  
  中国科学院长春光学精密机械与物理研究所中国科学院航空光学成像与测量重点实验室2.中国科学院大学
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132106.1576
  CLC： TP391.4
- Received：20 April 2012，
  
  Revised：19 June 2012，
  
  Published Online：20 June 2013，
  
  Published：15 June 2013
- 稿件说明：
移动端阅览
贾平李家德张叶. 采用非局部均值的超分辨率重构[J]. 光学精密工程, 2013,21(6): 1576-1585

JIA Ping LI Jia-de ZHANG Ye. Super-resolution reconstruction using nonlocal means[J]. Editorial Office of Optics and Precision Engineering, 2013,21(6): 1576-1585
贾平李家德张叶. 采用非局部均值的超分辨率重构[J]. 光学精密工程, 2013,21(6): 1576-1585 DOI： 10.3788/OPE.20132106.1576.

JIA Ping LI Jia-de ZHANG Ye. Super-resolution reconstruction using nonlocal means[J]. Editorial Office of Optics and Precision Engineering, 2013,21(6): 1576-1585 DOI： 10.3788/OPE.20132106.1576.

摘要

由于传统的超分辨率重构无法在工程应用中对含有局部运动图像进行有效的运动估计及重构，本文提出一种采用非局部均值(NLM)的超分辨率重构方案。简要介绍了具有较好去噪特性的非局部均值滤波器，分析了超分辨率重构的代价函数，根据构造出的非局部均值超分辨率重构算法的代价函数及其求解，对提出的方案进行进一步的优化和化简，最后得到一种易于工程实现的重构算法。实验结果表明，提出的算法不仅具有NLM算法的优点，即不需进行显式的运动估计就能得到更清晰、细节更丰富的重构图像；而且重构速度比简化前的NLM算法提高将近30%，有望应用于具有复杂运动的图像的超分辨率重构。

Abstract

As conventional super-resolution algorithms can not implement the motion estimation and reconstruction for an image with local motion in practical engineering applications

this paper proposed a super-resolution reconstruction algorithm based on NonLocal Means (NLM). First

the NLM filter

one of the successful denoising filters in recent years

was introduced briefly. Then

the details concerning its application to super-resolution were analyzed by creating a super-resolution cost function. By considering the practical situations and the need of the engineering facet

a scheme to simplify the procedure in the NLM super-resolution algorithm was proposed. The experiment results show that the simplified algorithm can not only effectively implement super-resolution reconstruction to get a clear and detailed image without explicit motion estimation

but also can obtain a reconstructed speed higher 30% than that of conventional algorithms. It can satisfy the practical needs of engineering set-tings and is expected to reconstruct the high resolution image with complex motion.

关键词

Keywords

references

TSAI R Y, HUANG T S. Multiframe image restoration and registration[J]. Advances in Computer Vision and Image Processing,1984,1: 317-339.[2]ELAD M, FEUER A. Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images [J].IEEE Transactions on Image Processing,1997, 6(12): 1646-1658.[3]ELAD M, HEL-OR Y. A fast super-resolution reconstruction algorithm for pure translational motion and common space-invariant blur[C]. Israel,2000:402-405.[4]HARDIE R C, BARNARD K J, ARMSTRONG E E. Joint MAP registration and high-resolution image estimation using a sequence of undersampled images[J]. IEEE Transactions on Image Processing, 1997, 6(12): 1621-1633.[5]RAJAN D, CHAUDHURI S. An MRF-based approach to generation of super-resolution images from blurred observations [J]. Springer Netherlands, 2002,16:5-15.[6]CHEESEMAN P, KANEFSKY B, KRAFT R, et al.. Super-resolved surface reconstruction from multiple images [C]. Santa Barbara, California,1996:293-308.[7]NHAT N, MILANFAR P, GOLUB G. A computationally efficient superresolution image reconstruction algorithm[J]. IEEE Transactions on Image Processing, 2001, 10(4): 573-583.[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]ZOMET A, RAV-ACHA A, PELEG S. Robust super-resolution[C]. Kauai,2001:645-650.[10]ZHANG L, YUAN Q, SHEN H, et al.. Multiframe image super-resolution adapted with local spatial information [J]. Journal of the Optical Society of America A, 2011, 28(3): 381-390.[11]LI X, HU Y, GAO X, et al.. A multi-frame image super-resolution method[J]. Signal Processing, 2010, 90(2): 405-414.[12]PURKAIT P, CHANDA B. Morphologic gain-controlled regularization for edge-preserving super-resolution image reconstruction [J]. Signal, Image and Video Processing,2011: 1-14.[13]JIN C, NUNEZ-YANEZ J, ACHIM A. Video super-resolution using generalized gaussian Markov Random Fields[J]. Signal Processing Letters, IEEE, 2012, 19(2): 63-66.[14]SU H, TANG L, WU Y, et al.. Spatially adaptive block-based super-resolution[J]. IEEE Transactions on Image Processing, 2012, 21(3): 1031-1045.[15]PELLETIER S, COOPERSTOCK J R. Preconditioning for edge-preserving image super resolution[J]. IEEE Transactions on Image Processing, 2012, 21(1): 67-79.[16]SU H, WU Y, ZHOU J. Super-resolution without Dense Flow[J]. IEEE Transactions on Image Processing, 2012,21(4):1782-1795.[17]ARICAN Z, FROSSARD P. Joint registration and super-resolution with omnidirectional images[J]. IEEE Transactions on Image Processing, 2011, 20(11): 3151-3162.[18]TIAN Y, YAP K, CHEN L. L1-norm multi-frame super-resolution from images with zooming motion[C]. Hangzhou,2011:1-6.[19]PATEL V, MODI C K, PAUNWALA C N, et al.. Hybrid approach for single image super resolution using ISEF and IBP [C]. Katra Jammu，2011:495-499.[20]KELLER S H, LAUZE F, NIELSEN M. Video super-resolution using simultaneous motion and intensity calculations [J]. IEEE Transactions on Image Processing, 2011, 20(7): 1870-1884.[21]姜伟，魏世衡. 反射型立体视觉系统的视差估计和图像复原[J]. 光学精密工程,2011,19(7):1701-1707.JIANG W, WEI S H. Disparity estimation and image restoration for reflection stereo vision[J]. Opt. Precision Eng., 2011,19(7):1701-1707.(in Chinese)[22]马冬冬，李金宗，朱兵，等. 并行图像复原与超分辨处理系统的设计与实现[J]. 光学精密工程,2009,17(5):1149-1160.MA D D, LI J Z, ZHU B, et al.. Implementation of parallel image restoration and super -resolution processing system [J]. Opt. Precision Eng., 2009,17(5):1149-1160.[23]徐正平，翟林培，葛文奇，等. 亚像元的CCD几何超分辨方法[J]. 光学精密工程,2008,16(12):2447-2453.XU Z P, ZHAI L P, GE W Q, et al.. CCD geometric superresolution method based on subpixel[J]. Opt. Precision Eng., 2008,16(12):2447-2453.(in Chinese)[24]MAHMOUDI M, SAPIRO G. Fast image and video denoising via nonlocal means of similar neighborhoods[J]. Signal Processing Letters,2005,12(12):839-842.[25]WANG J, JEON G, JEONG J. Deinterlacing algorithm with an advanced non-local means filter[J]. Optical Engineering,2012,51(4):47009.[26]NERCESSIAN S, PANETTA K A, AGAIAN S S. A multi-scale non-local means algorithm for image de-noising [C]. Baltimore, Maryland,SPIE, 2012:84010J-84060J.[27]BINEV P, BLANCO-SILVA F, BLOM D, et al.. High-quality Image Formation by Nonlocal Means Applied to High-Angle Annular Dark-Field Scanning Transmission Electron Microscopy (HAADF-STEM)[M]. Modeling Nanoscale Imaging in Electron Microscopy, Springer US, 2012.[28]TSCHUMPERL D, BRUN L. Non-Local Regularization and Registration of Multi-Valued Images By PDEs and Variational Methods on Higher Dimensional Spaces[M]. Mathematical Image Processing, Bergounioux M, Springer Berlin Heidelberg, 2011.[29]XIAOHUA Z, QIANG Z, JIAO L C. Image denoising with non-local means in the shearlet domain[C]. Xiamen, 2011:1-5.[30]YONG S K, HWASUP L, OUK C, et al.. Separable bilateral nonlocal means [C]. Brussels, Belguim, 2011:1513-1516.[31]BUADES A, COLL B, MOREL J M. A non-local algorithm for image denoising[C]. San Diego, 2005:60-65.[32]PROTTER M, ELAD M, TAKEDA H, et al.. Generalizing the nonlocal-means to super-resolution reconstruction [J]. IEEE Transactions on Image Processing, 2009,18(1):36-51.[33]BUADES A, COLL B, MOREL J M. Denoising image sequences does not require motion estimation[C]. Como: 2005:70-74.[34]FARSIU S. Robust shift and add approach to superresolution [J]. Proceedings of SPIE,2003,5203(1):121-130.[35]吴琼. 可见光图像超分辨率客观评价方法研究[D]. 北京: 首都师范大学, 2009.WU Q. Scientific super-resolution objective evaluation index and method system[D]. Beijing: Capital Normal University, 2009.(in Chinese)

Views

493

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Two-channel photonic crystal filter system

Image super-resolution network based on multi-scale adaptive attention

Image super-resolution reconstruction based on attention and wide-activated dense residual network

Generate adversarial network for super-resolution reconstruction of remote sensing images by fusing edge enhancement and non-local modules

Polarization computational imaging super-resolution reconstruction with lightweight attention cascading network

Related Author

LIU Jie

LU Huidong

ZHAO Jun

DONG Jie

HU Yanmei

WEN Jianrong

XING Qi

LI Penghui

Related Institution

School of Energy and Electrical Engineering， Qinghai University

School of Microelectronics， Shanxi University of Electronic Science and Technology

China Hebei Control Engineering Research Center

School of Artificial Intelligence， Hebei University of Technology

School of Information and Control Engineering，China University of Mining and Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰