WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-res...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
16.09.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks (\(4\times\)). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR. |
---|---|
AbstractList | Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks (\(4\times\)). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR. |
Author | Jeevan, Pranav Nixon, Neeraj Sethi, Amit |
Author_xml | – sequence: 1 givenname: Pranav surname: Jeevan fullname: Jeevan, Pranav – sequence: 2 givenname: Neeraj surname: Nixon fullname: Nixon, Neeraj – sequence: 3 givenname: Amit surname: Sethi fullname: Sethi, Amit |
BookMark | eNrjYmDJy89LZWLgNDI2NtS1MDEy4mDgLS7OMjAwMDIzNzI1NeZksA9PLEv1zawIDtINM7JScM3LSMxLzsxLVwguLUgt0i1KLc7PKS3JzM9TKM8syVDwyEzPSC1ScE1Ly0zOTM1LruRhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXhjQwMzoJ0WhibGxKkCAPOXOeI |
ContentType | Paper |
Copyright | 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni Edition) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content (ProQuest) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_31065538143 |
IEDL.DBID | 8FG |
IngestDate | Thu Sep 19 05:42:34 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_31065538143 |
OpenAccessLink | https://www.proquest.com/docview/3106553814/abstract/?pq-origsite=%requestingapplication% |
PQID | 3106553814 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_3106553814 |
PublicationCentury | 2000 |
PublicationDate | 20240916 |
PublicationDateYYYYMMDD | 2024-09-16 |
PublicationDate_xml | – month: 09 year: 2024 text: 20240916 day: 16 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2024 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.554793 |
SecondaryResourceType | preprint |
Snippet | Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Discrete Wavelet Transform Efficiency Image enhancement Image resolution Mixers |
Title | WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency |
URI | https://www.proquest.com/docview/3106553814/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEB5qF8GbT3zUEtBrWDebpK6XgrJrEbaU1kdvJdmm6mWt7VY8-dudWXf1IPQYEiYkTOb5zQTgXBjjwkhecjSJHJdaSB45nXECYCibqcAqqndO-7r3IO_GatyAXl0LQ7DKWiaWgnr6llGM3EczRCt8nYH0jaUoQFb43fk7p_-jKM9afaaxAV5APfGoZjy5_Y22CN1B2zn8J3BLLZJsgzcwc7fYgYbLd2GzBF9myz3oPpkPl75-job8UVyxOH-hJhj5MxutcDlHh7jiD0ZRU_YDzWBx2fyBKif34SyJ7296vN51UnHIcvJ3nvAAmujqu0NgmtJikvSmUdIKdC86MppNlZnpCxNG9gha6ygdr58-gS2BpAntEOgWNIvFyp2iSi1su7ytNnjXcX8wxFH6FX8DcuOAFQ |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8MwDLZgE4IbT8EYEAmuETRNMsplB9RSYJ0QG7BblXYZcOnGuiF-PnbJ4IC0c6JYiRw_P9sAZ8IY6wfykqNJZLnUQvLA6pwTAENlufIyRfXOSVfHT_JuoAYu4FY6WOVCJlaCejjOKUZ-jmaIVvg7PdmefHCaGkXZVTdCYxXq0kfVSZXi0c1vjEXoFlrM_j8xW-mOaBPqD2Zip1uwYottWKsgl3m5A-0X82mT96_eI38WVyws3qj1RfHKenPcztENdlzBKFbKfgAZLKxaPlC95C6cRmH_OuYLqqnjizL9u4W_BzV08O0-ME3JMEna0iiZCXQqWjIYDZUZ6QvjB9kBNJed1Fi-fALrcT_ppJ3b7v0hbAgkQ3gHTzehNpvO7REq1Vl2XL3cN1HffHg |
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%3Ajournal&rft.genre=article&rft.atitle=WaveMixSR-V2%3A+Enhancing+Super-resolution+with+Higher+Efficiency&rft.jtitle=arXiv.org&rft.au=Jeevan%2C+Pranav&rft.au=Nixon%2C+Neeraj&rft.au=Sethi%2C+Amit&rft.date=2024-09-16&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |