No Detail Found!

An Extensive Review of Developments and Methods in Super-Resolution Image Reconstruction

Author(s)
Radha Shinde CSE Sage University Indore
Atul Nandwal CSE Sage University Indore
Abstract
Super-resolution (SR) image reconstruction plays a vital role in enhancing the resolution of low-resolution (LR) images, benefiting various fields such as remote sensing, medical imaging, and surveillance. The SR problem entails reconstructing high-resolution (HR) images from LR inputs, typically due to the loss of high-frequency information and the problem's ill-posed nature. This review study presents a comprehensive overview of recent developments and approaches in SR image reconstruction. This study primarily presents three approaches: methods based on learning, methods based on reconstruction, and methods based on interpolation. Despite the fact that interpolation-based approaches, such as bicubic interpolation, are straightforward and quick, they frequently result in blurring and loss of high-frequency features. Reconstruction-based methods leverage prior knowledge of image characteristics to recover HR images, often through optimization techniques. However, these methods may suffer from slow convergence and high computational cost. Because of their capacity to learn complicated mappings between LR and HR picture spaces, learning-based methods-and deep learning approaches in particular-have been the center of a lot of attention lately. These methods leverage large datasets to train convolutional neural networks (CNNs) for image super-resolution, achieving remarkable performance in terms of visual quality and computational efficiency. Furthermore, we discuss the challenges and future directions in SR research, including the development of more robust and efficient algorithms, handling noisy realworld data, and exploring novel architectures and loss functions to further improve SR performance. The purpose of this review paper is to provide a comprehensive overview of strategies for SR image reconstruction. It focuses on the progression from conventional interpolation methods to cutting-edge deep learning approaches. They hope that this publication will serve as a valuable resource for scholars and practitioners in the field of computer vision and image processing.
Publication Details
Page(s) 1460-1475
DOI DOI not available
Published Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: 4, Year: 2024

Request the full text from PASTIC

Keywords
High-resolution images, Interpolation-based methods, Image reconstruction, Super-resolution, Lowresolution images
References
Jo Y.,Kim S.J.,TN S.J. . .Practical single-image super-resolution using look-up table. In Proceedings of the IEEE/CVF Conference on Computer Vision, : 691-700.
Loghmani ,Zaini A.M.E.,Latif A. .2018 .ImageZoomingUsingBarycentricRationalIn terpolation. J.Math.Ext, 12 : 67-86.
Cherifi T.,Hamami-Metiche L.,Kerrouchi S. . .Comparative study between superresolution based on polynomial interpolations and Whittaker filtering interpolations. El-Oued , Algeria, : 235-241.
Xu Y.,Li J.,Du H.,L. H. .2021 .Single-Image Super-Resolution Using Panchromatic Gradient Prior and Variational Model. Math. Probl. Eng, : 9944385.
Huang Y.,Li J.,Gao X.,He L.,Lu W. .2018 .Single image super-resolution via multiple mixture prior models. IEEE Trans. Image Process, 27 : 5904-5917.
Yang Q.,Zhao Y.,Chen T.,Y.Q. T. .2018 .Single image super-resolution using selfoptimizing mask via fractional-order gradientinterpolation and reconstruction. ISA Trans, 82 : 163-171.
Xiong M.,Song Y.,Xiang Y.,Xie B.,Deng Z. .2021 .Anchor neighborhood embedding based single-image super-resolution reconstruction with similarity threshold adjustment. In Proceedings of the 2021 2nd International Conference on Artificial Intelligence and Information Systems, : 1-8.
Hardiansyah B.,Lu Y. .2021 .Single image super-resolution via multiple linear mapping anchored neighborhood regression. Multimed. Tools Appl, 80 : 28713-28730.
Liu Y.,Wu H.,Wang J.,Li X.,C. X. .2021 .Single image super-resolution using feature adaptive learning and global structuresparsity. SignalProcess, 188 : 108184.
Wang L.,Du J.,Gholipour A.,Zhu H.,He Z.,Jia Y. .01973 .3D dense convolutional neural network for fast and accurate single MRimagesuperresolution. J.Comput.Med, 93 : .
Lei S.,Shi Z.,Zou Z. .2017 .Super-resolution for remote sensing images via local-global combined network. IEEE Geosci. Remote Sens. Lett, 14 : 1243-1247.
Guo Y.,Chen J.,Wang J.,Chen Q.,Cao J.,Deng Z.,Xu Y.,Tan M. . .Closedloop matters: Dual regression networks for single imagesuperresolution. InProceedingsoftheIEEE/CVFConferenceonComputerVisionandPatter n Recognition, : 5407-5416.
Wang Z.,Chen J.,S.C. J. .2020 .Deep learning for image superresolution:Asurvey. , 43 : 3365-3387.
Tian C.,Zhang X.,Lin J.C.W.,W. J.C.W.,Y. J.C.W. . .GenerativeAdversarialNetwor ksforImageSuper-Resolution:ASurvey. , : 13620.
Chen ,He X.,Qing L.,Wu Y.,Ren C.,Sheriff R.E.,Zhu C.,Liu C.,Ruan Z.,Zhao P.,Dong C.,Shang F.,Liu Y.,Yang L.,Timofte R. .2022 .Videosuper - resolutionbasedondeeplearning: A comprehensive survey. Artif. Intell. Rev, 79 : 1-55.
Yan B.,Bare B.,Li C.,Tan K.,W. K. .2019 .DeepObjectiveQualityAssessmentDrivenSing leImageSuper-Resolution. IEEETrans. Multimed, 21 : 2957-2971.
LeCun ,Bengio Y.,Hinton Y. . .. G.Deeplearning.Nature2015, 521 : 436-444.
Abiodun O.I.,Jantan A.,Omolara A.E.,Dada K.V.,Mohamed N.A.,Arshad H. .2018 .S tate-of-theartinartificialneuralnetwork applications: A survey. Heliyon, 4 : e00938.
Bengio Y.,Courville A.C.,Vincent P. .2013 .Representation Learning: A Review and New Perspectives. IEEE Trans. Pattern Anal. Mach. Intell, 35 : 1798-1828.
Arbelaez P.,Maire M.,Fowlkes C.,Malik J. .2010 .Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell, 33 : 898-916.
Agustsson ,Timofte R.,HI R. . .Ntire2017challenge on single image superresolution:Datasetandstudy. , : 126-135.
Zeyde M.,Protter M. .2010 .On single image scale-up using sparserepresentations. In Proceedings of the International Conference on Curves and Surfaces, : 711-730.
Huang J.B.,Singh A.,Ahuja N. . .Single image super-resolution from transformed selfexemplars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, : 5197-5206.
Xia G.S.,Hu J.,Hu F.,Shi B.,Bai X.,Zhong Y.,Lu X. .2017 .AID: A benchmark data set for performance evaluation of aerial scene classification. IEEETrans. Geosci. RemoteSens, 55 : 3965-3981.
Dai D.,Yang W. .2010 .Satellite image classification via two-layer sparse coding with biased image representation. IEEE Geosci. Remote Sens. Lett, 8 : 173-176.
Wang X.,Yu K.,Dong C.,Loy C.C.,UT C.C. . .Recovering realistic texture in image superresolutionbydeepspatialfeaturetransform. In Proceedings of the IEEE Conference on Computer Vision, : 606-615.
Yang Y.,Newsam S. . .Bag-of-visual-words and spatial extensions for land-use classification. In Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, : 270-279.
Lu J,X. J . .RemoteSensingImageSceneClassification:BenchmarkandS tateoftheArt. Proc.IEEE2017, 105 : 1865-1883.
Zhao L.,Tang P.,Huo L. .2016 .Feature significance-based multibag-of-visual-words model for remote sensing image scene classification. J. Appl. Remote Sens, 10 : 035004.
Yang ,Wright J.,T.S. J.,Imagesuperresolutionviasparserepresentation.IEEETrans .ImageProcess Y. .2010 .. , 19 : 2861-2873.
Fujimoto A.,Ogawa T.,Yamamoto K.,Matsui Y.,Yamasaki T.,Aizawa K. . .Manga109 dataset and creation of metadata. In Proceedings of the 1st International Workshop on Comics Analysis, Processing and Understanding, 4 : 1-5.
Chen C.,Xiong Z.,Tian X.,Zha Z.J.,Wu F. . .Camera lens super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, : 1652-1660.
Everingham M.,Eslami S.; Van,Gool L.,Williams C.K.,Winn J.,Zisserman A. .2015 .The pascal visual object classes challenge: A retrospective. Int.J.Comput.Vis, 111 : 98-136.
Wang Z.,Bovik A.C.,Sheikh H.R.,Simoncelli E.P. .2004 .Image quality assessment:From error visibility to structural similarity. IEEE Trans. Image Process, 13 : 600-612.
Mittal A.,Soundararajan R.,Bovik A.C.,Making A.C. .2013 .a “Completely Blind “Image Quality Analyzer. , 20 : 209-212.
Qiu Y.,Wang R.,J. R. . .Embedded block residual network: A recursive restoration model for single-image super- resolution. November2019, 27 : 4180-4189.
Li J.,Mei Y.,Fang K.,F. K. . .LightweightandAccurateRecursiveFractalNetworkforIm ageSuper-Resolution. November2019, 27 : 3814-3823.
Luo Z.,Huang Y.,Li S.,Wang L.,Tan T. . .Efficient Super Resolution by Recursive Aggregation. In Proceedings of the 2020 25thInternational Conference on Pattern Recognition (ICPR), : 8592-8599.
Gao ,Wang Z.,Li J.,Li W.,Yu Y.,Zeng T. . .LightweightBimodalNetworkforSingl e-ImageSuper-ResolutionviaSymmetric CNN and Transformer. , : 13286.
He K.,Zhang X.,Ren S.,Sun J.Deepresiduallearningforimagerecognition.,NV J.Deepresiduallearningforimagerecognition. . .InProcee dingsoftheIEEEConferenceon Computer Vision. , : 770-778.
Zhang ,Tian Y.,Kong Y.,Zhong B.,Fu Y. . .ResidualDenseNetworkforImageSuper - Resolution. , : 2472-2481.
Liu J.,Tang Y.,J. Y.,G. Y. . .Residualfeatureaggregationnetworkforim agesuperresolution. InProceedingsof the IEEE/CVF Conference on Computer Vision, : 2359-2368.
He K.,Zhang X.,Ren S.,Sun J. .2016 .Identity mappings in deep residual networks. In Proceedings of the European Conference on Computer Vision, : 630-645.
Liu D.,Li J.,Yuan Q. .2021 .A Spectral Grouping and Attention-Driven Residual Dense Network for Hyperspectral Image SuperResolution. IEEETrans.Geosci.RemoteSens, 59 : 7711-7725.
Liu ,Tang J.,G. J. .2020 .Residual Feature Distillation Network for Lightweight Image SuperResolution. In Proceedings of the European conference on computer vision, : 41-55.
Lai ,Huang J.B.,Ahuja N.,Yang M.H.,Deep Laplacian M.H. . .Pyramid Networks for Fast and Accurate Super-Resolution. , : .
0

Citations

0

Downloads

52

Views