A Comprehensive Review of Deep Learning-based Single Image Super-resolution

Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution, especially by utilizing deep learning methods. This survey i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bashir, Syed Muhammad Arsalan, Wang, Yi, Khan, Mahrukh, Niu, Yilong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Bashir, Syed Muhammad Arsalan
Wang, Yi
Khan, Mahrukh
Niu, Yilong
description Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution, especially by utilizing deep learning methods. This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution. The survey classifies the image SR methods into four categories, i.e., classical methods, supervised learning-based methods, unsupervised learning-based methods, and domain-specific SR methods. We also introduce the problem of SR to provide intuition about image quality metrics, available reference datasets, and SR challenges. Deep learning-based approaches of SR are evaluated using a reference dataset. Some of the reviewed state-of-the-art image SR methods include the enhanced deep SR network (EDSR), cycle-in-cycle GAN (CinCGAN), multiscale residual network (MSRN), meta residual dense network (Meta-RDN), recurrent back-projection network (RBPN), second-order attention network (SAN), SR feedback network (SRFBN) and the wavelet-based residual attention network (WRAN). Finally, this survey is concluded with future directions and trends in SR and open problems in SR to be addressed by the researchers.
doi_str_mv 10.48550/arxiv.2102.09351
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2102_09351</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2102_09351</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-a9461159b1d7482d8a0747a12e420178fae0902258c328c2589ad11790d09c9e3</originalsourceid><addsrcrecordid>eNotz8tOwzAQhWFvWKCWB2CFX8DB49i1vazCrSISEu0-msaT1lJucmiAt6cUVv9ZHelj7BZkpp0x8h7TV5wzBVJl0ucGrtnrmhdDNyY6Uj_Fmfg7zZE--dDwB6KRl4Spj_1B7HGiwLfn2RLfdHggvj2NlESiaWhPH3Hol-yqwXaim_8u2O7pcVe8iPLteVOsS4ErCwK9XgEYv4dgtVPBobTaIijSSoJ1DZL0Uinj6ly5-lyPAcB6GaSvPeULdvd3e9FUY4odpu_qV1VdVPkP4xBF_g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Comprehensive Review of Deep Learning-based Single Image Super-resolution</title><source>arXiv.org</source><creator>Bashir, Syed Muhammad Arsalan ; Wang, Yi ; Khan, Mahrukh ; Niu, Yilong</creator><creatorcontrib>Bashir, Syed Muhammad Arsalan ; Wang, Yi ; Khan, Mahrukh ; Niu, Yilong</creatorcontrib><description>Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution, especially by utilizing deep learning methods. This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution. The survey classifies the image SR methods into four categories, i.e., classical methods, supervised learning-based methods, unsupervised learning-based methods, and domain-specific SR methods. We also introduce the problem of SR to provide intuition about image quality metrics, available reference datasets, and SR challenges. Deep learning-based approaches of SR are evaluated using a reference dataset. Some of the reviewed state-of-the-art image SR methods include the enhanced deep SR network (EDSR), cycle-in-cycle GAN (CinCGAN), multiscale residual network (MSRN), meta residual dense network (Meta-RDN), recurrent back-projection network (RBPN), second-order attention network (SAN), SR feedback network (SRFBN) and the wavelet-based residual attention network (WRAN). Finally, this survey is concluded with future directions and trends in SR and open problems in SR to be addressed by the researchers.</description><identifier>DOI: 10.48550/arxiv.2102.09351</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2021-02</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2102.09351$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2102.09351$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bashir, Syed Muhammad Arsalan</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Khan, Mahrukh</creatorcontrib><creatorcontrib>Niu, Yilong</creatorcontrib><title>A Comprehensive Review of Deep Learning-based Single Image Super-resolution</title><description>Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution, especially by utilizing deep learning methods. This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution. The survey classifies the image SR methods into four categories, i.e., classical methods, supervised learning-based methods, unsupervised learning-based methods, and domain-specific SR methods. We also introduce the problem of SR to provide intuition about image quality metrics, available reference datasets, and SR challenges. Deep learning-based approaches of SR are evaluated using a reference dataset. Some of the reviewed state-of-the-art image SR methods include the enhanced deep SR network (EDSR), cycle-in-cycle GAN (CinCGAN), multiscale residual network (MSRN), meta residual dense network (Meta-RDN), recurrent back-projection network (RBPN), second-order attention network (SAN), SR feedback network (SRFBN) and the wavelet-based residual attention network (WRAN). Finally, this survey is concluded with future directions and trends in SR and open problems in SR to be addressed by the researchers.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8tOwzAQhWFvWKCWB2CFX8DB49i1vazCrSISEu0-msaT1lJucmiAt6cUVv9ZHelj7BZkpp0x8h7TV5wzBVJl0ucGrtnrmhdDNyY6Uj_Fmfg7zZE--dDwB6KRl4Spj_1B7HGiwLfn2RLfdHggvj2NlESiaWhPH3Hol-yqwXaim_8u2O7pcVe8iPLteVOsS4ErCwK9XgEYv4dgtVPBobTaIijSSoJ1DZL0Uinj6ly5-lyPAcB6GaSvPeULdvd3e9FUY4odpu_qV1VdVPkP4xBF_g</recordid><startdate>20210218</startdate><enddate>20210218</enddate><creator>Bashir, Syed Muhammad Arsalan</creator><creator>Wang, Yi</creator><creator>Khan, Mahrukh</creator><creator>Niu, Yilong</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210218</creationdate><title>A Comprehensive Review of Deep Learning-based Single Image Super-resolution</title><author>Bashir, Syed Muhammad Arsalan ; Wang, Yi ; Khan, Mahrukh ; Niu, Yilong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-a9461159b1d7482d8a0747a12e420178fae0902258c328c2589ad11790d09c9e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Bashir, Syed Muhammad Arsalan</creatorcontrib><creatorcontrib>Wang, Yi</creatorcontrib><creatorcontrib>Khan, Mahrukh</creatorcontrib><creatorcontrib>Niu, Yilong</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bashir, Syed Muhammad Arsalan</au><au>Wang, Yi</au><au>Khan, Mahrukh</au><au>Niu, Yilong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Comprehensive Review of Deep Learning-based Single Image Super-resolution</atitle><date>2021-02-18</date><risdate>2021</risdate><abstract>Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution, especially by utilizing deep learning methods. This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution. The survey classifies the image SR methods into four categories, i.e., classical methods, supervised learning-based methods, unsupervised learning-based methods, and domain-specific SR methods. We also introduce the problem of SR to provide intuition about image quality metrics, available reference datasets, and SR challenges. Deep learning-based approaches of SR are evaluated using a reference dataset. Some of the reviewed state-of-the-art image SR methods include the enhanced deep SR network (EDSR), cycle-in-cycle GAN (CinCGAN), multiscale residual network (MSRN), meta residual dense network (Meta-RDN), recurrent back-projection network (RBPN), second-order attention network (SAN), SR feedback network (SRFBN) and the wavelet-based residual attention network (WRAN). Finally, this survey is concluded with future directions and trends in SR and open problems in SR to be addressed by the researchers.</abstract><doi>10.48550/arxiv.2102.09351</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2102.09351
ispartof
issn
language eng
recordid cdi_arxiv_primary_2102_09351
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
title A Comprehensive Review of Deep Learning-based Single Image Super-resolution
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T07%3A08%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Comprehensive%20Review%20of%20Deep%20Learning-based%20Single%20Image%20Super-resolution&rft.au=Bashir,%20Syed%20Muhammad%20Arsalan&rft.date=2021-02-18&rft_id=info:doi/10.48550/arxiv.2102.09351&rft_dat=%3Carxiv_GOX%3E2102_09351%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true