Seven Ways to Improve Example-Based Single Image Super Resolution

In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2) use of large dictionaries with efficient search structures, 3) cascading, 4) image self-similarities, 5) back projection refinement, 6) enhanc...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 1865 - 1873
Hlavní autoři: Timofte, Radu, Rothe, Rasmus, Van Gool, Luc
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2016
Témata:
Dictionaries
Encoding
Image reconstruction
Image resolution
Testing
Training
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2) use of large dictionaries with efficient search structures, 3) cascading, 4) image self-similarities, 5) back projection refinement, 6) enhanced prediction by consistency check, and 7) context reasoning. We validate our seven techniques on standard SR benchmarks (i.e. Set5, Set14, B100) and methods (i.e. A+, SRCNN, ANR, Zeyde, Yang) and achieve substantial improvements. The techniques are widely applicable and require no changes or only minor adjustments of the SR methods. Moreover, our Improved A+ (IA) method sets new stateof-the-art results outperforming A+ by up to 0.9dB on average PSNR whilst maintaining a low time complexity.
AbstractList In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2) use of large dictionaries with efficient search structures, 3) cascading, 4) image self-similarities, 5) back projection refinement, 6) enhanced prediction by consistency check, and 7) context reasoning. We validate our seven techniques on standard SR benchmarks (i.e. Set5, Set14, B100) and methods (i.e. A+, SRCNN, ANR, Zeyde, Yang) and achieve substantial improvements. The techniques are widely applicable and require no changes or only minor adjustments of the SR methods. Moreover, our Improved A+ (IA) method sets new stateof-the-art results outperforming A+ by up to 0.9dB on average PSNR whilst maintaining a low time complexity.
Author Rothe, Rasmus
Van Gool, Luc
Timofte, Radu
Author_xml – sequence: 1
  givenname: Radu
  surname: Timofte
  fullname: Timofte, Radu
  email: radu.timofte@vision.ee.ethz.ch
  organization: CVL, ETH Zurich, Zurich, Switzerland
– sequence: 2
  givenname: Rasmus
  surname: Rothe
  fullname: Rothe, Rasmus
  email: rrothe@vision.ee.ethz.ch
  organization: CVL, ETH Zurich, Zurich, Switzerland
– sequence: 3
  givenname: Luc
  surname: Van Gool
  fullname: Van Gool, Luc
  email: vangool@vision.ee.ethz.ch
  organization: ETH Zurich, KU Leuven, Zurich, Switzerland
BookMark eNotjMtKw0AUQEdRsNYsXbmZH0i9N8m8ljW0WigojY9luUnulEheJG2xf29BN-csDpxbcdV2LQtxjzBDBPeYfr5tZhGgPkNfiMAZi4k2sbUK8VJMEHQcaofuRgTj-A0A6LRF6yZinvGRW_lFp1HuO7lq-qE7slz8UNPXHD7RyKXMqnZX8znSjmV26HmQGx67-rCvuvZOXHuqRw7-PRUfy8V7-hKuX59X6XwdVhHYfeiRCvQONTrnbWR8DjE78oV3lHvIgRhKBEiKItGUlIlCXypHqjSRp9LGU_Hw962YedsPVUPDaWuMBWVU_AvCaUv-
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2016.206
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 9781467388511
1467388513
EISSN 1063-6919
EndPage 1873
ExternalDocumentID 7780575
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
ID FETCH-LOGICAL-i208t-f1ac1f916199f827fb03e9afcf9abf0b0ae0d1004cc46a4d451fd59a5d72fad83
IEDL.DBID RIE
ISICitedReferencesCount 303
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000400012301098&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:33:58 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i208t-f1ac1f916199f827fb03e9afcf9abf0b0ae0d1004cc46a4d451fd59a5d72fad83
PageCount 9
ParticipantIDs ieee_primary_7780575
PublicationCentury 2000
PublicationDate 2016-June
PublicationDateYYYYMMDD 2016-06-01
PublicationDate_xml – month: 06
  year: 2016
  text: 2016-June
PublicationDecade 2010
PublicationTitle 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublicationTitleAbbrev CVPR
PublicationYear 2016
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001968189
ssj0023720
ssj0003211698
Score 2.5558417
Snippet In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2)...
SourceID ieee
SourceType Publisher
StartPage 1865
SubjectTerms Dictionaries
Encoding
Image reconstruction
Image resolution
Testing
Training
Title Seven Ways to Improve Example-Based Single Image Super Resolution
URI https://ieeexplore.ieee.org/document/7780575
WOSCitedRecordID wos000400012301098&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07a8MwEBZJ6NApbZPSNxo6Vo0syZK1NiR0CqHPbEFPCJQkxE5p_30l23EodOlmncxhdJZOOt19HwC3NLOJFlgirZVFjFiGJFcSMYVN5q1OOFEl2YSYTLLZTE5b4K6phXHOlcln7j4-lnf5dmW2MVQ2EBGAX6Rt0BaCV7Va-3iK5MH3yKZNw8mGy-ZGgUQ2lj3G5mD4Nn2KiV0xS4H_YlYpHcu4-79POgL9fYUenDa-5xi03PIEdOstJawnbB5EO9aGnawXFtII2gTf1XcOixWsogoOjr5UBApGD8GtBQ1B64cLnWG5gc_bdVAQA_3Vb9oHr-PRy_AR1UQKaEFwViCfKJP4sBFMpPQZEV5j6qTyxkulPdZYOWwjdJwxjCtmWZp4m0qVWkG8shk9BZ3launOAOSUCqoU4QY7FqazpsHIMvOMGJ6GV89BLw7SfF1hZczr8bn4W3wJDqMNqtSrK9ApNlt3DQ7MZ7HINzelgX8AdiOlDQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4QTfSECsa3PXi00m273e1VgsGIhCgqN9JnQmKAwGL039vuwhITL962081k09l22unM9wFwTVMTqQQLpJQ0iBHDkOBSICaxTp1REScyJ5tIer10OBT9Crgpa2GstXnymb0Nj_ldvpnqZQiVNZMAwJ_EW2A7ZozgolprE1ER3HsfUbapP9twUd4pkMDHskHZbLbe-s8htSvkKfBf3Cq5a7mv_e-j9kFjU6MH-6X3OQAVOzkEtdWmEq6m7MKL1rwNa1ndL6UBtgm-y-8FzKawiCtY2P6SASoY3XnH5jV4rR_Wd_oFB74sZ15BCPUXP2oDvN63B60OWlEpoDHBaYZcJHXk_FYwEsKlJHEKUyuk005I5bDC0mITwOO0Zlwyw-LImVjI2CTESZPSI1CdTCf2GEBOaUKlJFxjy_yEVtSbWaSOEc1j_-oJqIdBGs0KtIzRanxO_xZfgd3O4Kk76j70Hs_AXrBHkYh1DqrZfGkvwI7-zMaL-WVu7B8826hU
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2016+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29&rft.atitle=Seven+Ways+to+Improve+Example-Based+Single+Image+Super+Resolution&rft.au=Timofte%2C+Radu&rft.au=Rothe%2C+Rasmus&rft.au=Van+Gool%2C+Luc&rft.date=2016-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=1865&rft.epage=1873&rft_id=info:doi/10.1109%2FCVPR.2016.206&rft.externalDocID=7780575