APPARATUS AND METHOD FOR IMPROVING PERFORMANCE OF SUPER RESOLUTION FOR PREVIOUSLY UNSEEN IMAGES

APPARATUS AND METHOD FOR IMPROVING PERFORMANCE OF SUPER RESOLUTION FOR PREVIOUSLY UNSEEN IMAGES

Described is an apparatus (500) for training an image cleaning model, the apparatus (500) comprising one or more processors (501) configured to: receive a first clean low resolution image (102); stochastically corrupt the first clean tow resolution image (102) to generate a corrupted tow resolution...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: FILIPPOV, Alexander Nikolaevich, ROMERO, VERGARA Andres Felipe, VAN, GOOL Luc, TIMOFTE, Radu
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
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 FILIPPOV, Alexander Nikolaevich
ROMERO, VERGARA Andres Felipe
VAN, GOOL Luc
TIMOFTE, Radu
description Described is an apparatus (500) for training an image cleaning model, the apparatus (500) comprising one or more processors (501) configured to: receive a first clean low resolution image (102); stochastically corrupt the first clean tow resolution image (102) to generate a corrupted tow resolution image (103); clean the corrupted low resolution image (103) to generate a second clean tow resolution image (105); compare the first clean tow resolution image (102) with the second clean tow resolution image (105); and adapt the image cleaning mode) in dependence on the comparison between the first clean tow resolution image (102) and the second clean tow resolution image (105). By stochastically corrupting the first clean tow resolution image (102), the image cleaning model may be able to team how to clean corrupted tow resolution image (103).
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4302257A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4302257A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4302257A13</originalsourceid><addsrcrecordid>eNqNi0sKwjAUALNxIeod3gUEbRXXj_alDTR5IZ-Cq1AkrkQL9f4YxAO4Ghhm1iKhtegwRA9oWtAUem5BsgOlreNRmQ4suSI0moaAJfhYBDjyPMSg2Hxr62hUHP1whWg8kSk_duS3YnWfHkve_bgRICk0_T7Pr5SXebrlZ34nsqf6UFXnCx7rP5IPJaozOg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>APPARATUS AND METHOD FOR IMPROVING PERFORMANCE OF SUPER RESOLUTION FOR PREVIOUSLY UNSEEN IMAGES</title><source>esp@cenet</source><creator>FILIPPOV, Alexander Nikolaevich ; ROMERO, VERGARA Andres Felipe ; VAN, GOOL Luc ; TIMOFTE, Radu</creator><creatorcontrib>FILIPPOV, Alexander Nikolaevich ; ROMERO, VERGARA Andres Felipe ; VAN, GOOL Luc ; TIMOFTE, Radu</creatorcontrib><description>Described is an apparatus (500) for training an image cleaning model, the apparatus (500) comprising one or more processors (501) configured to: receive a first clean low resolution image (102); stochastically corrupt the first clean tow resolution image (102) to generate a corrupted tow resolution image (103); clean the corrupted low resolution image (103) to generate a second clean tow resolution image (105); compare the first clean tow resolution image (102) with the second clean tow resolution image (105); and adapt the image cleaning mode) in dependence on the comparison between the first clean tow resolution image (102) and the second clean tow resolution image (105). By stochastically corrupting the first clean tow resolution image (102), the image cleaning model may be able to team how to clean corrupted tow resolution image (103).</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240110&amp;DB=EPODOC&amp;CC=EP&amp;NR=4302257A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240110&amp;DB=EPODOC&amp;CC=EP&amp;NR=4302257A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>FILIPPOV, Alexander Nikolaevich</creatorcontrib><creatorcontrib>ROMERO, VERGARA Andres Felipe</creatorcontrib><creatorcontrib>VAN, GOOL Luc</creatorcontrib><creatorcontrib>TIMOFTE, Radu</creatorcontrib><title>APPARATUS AND METHOD FOR IMPROVING PERFORMANCE OF SUPER RESOLUTION FOR PREVIOUSLY UNSEEN IMAGES</title><description>Described is an apparatus (500) for training an image cleaning model, the apparatus (500) comprising one or more processors (501) configured to: receive a first clean low resolution image (102); stochastically corrupt the first clean tow resolution image (102) to generate a corrupted tow resolution image (103); clean the corrupted low resolution image (103) to generate a second clean tow resolution image (105); compare the first clean tow resolution image (102) with the second clean tow resolution image (105); and adapt the image cleaning mode) in dependence on the comparison between the first clean tow resolution image (102) and the second clean tow resolution image (105). By stochastically corrupting the first clean tow resolution image (102), the image cleaning model may be able to team how to clean corrupted tow resolution image (103).</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi0sKwjAUALNxIeod3gUEbRXXj_alDTR5IZ-Cq1AkrkQL9f4YxAO4Ghhm1iKhtegwRA9oWtAUem5BsgOlreNRmQ4suSI0moaAJfhYBDjyPMSg2Hxr62hUHP1whWg8kSk_duS3YnWfHkve_bgRICk0_T7Pr5SXebrlZ34nsqf6UFXnCx7rP5IPJaozOg</recordid><startdate>20240110</startdate><enddate>20240110</enddate><creator>FILIPPOV, Alexander Nikolaevich</creator><creator>ROMERO, VERGARA Andres Felipe</creator><creator>VAN, GOOL Luc</creator><creator>TIMOFTE, Radu</creator><scope>EVB</scope></search><sort><creationdate>20240110</creationdate><title>APPARATUS AND METHOD FOR IMPROVING PERFORMANCE OF SUPER RESOLUTION FOR PREVIOUSLY UNSEEN IMAGES</title><author>FILIPPOV, Alexander Nikolaevich ; ROMERO, VERGARA Andres Felipe ; VAN, GOOL Luc ; TIMOFTE, Radu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4302257A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>FILIPPOV, Alexander Nikolaevich</creatorcontrib><creatorcontrib>ROMERO, VERGARA Andres Felipe</creatorcontrib><creatorcontrib>VAN, GOOL Luc</creatorcontrib><creatorcontrib>TIMOFTE, Radu</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>FILIPPOV, Alexander Nikolaevich</au><au>ROMERO, VERGARA Andres Felipe</au><au>VAN, GOOL Luc</au><au>TIMOFTE, Radu</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>APPARATUS AND METHOD FOR IMPROVING PERFORMANCE OF SUPER RESOLUTION FOR PREVIOUSLY UNSEEN IMAGES</title><date>2024-01-10</date><risdate>2024</risdate><abstract>Described is an apparatus (500) for training an image cleaning model, the apparatus (500) comprising one or more processors (501) configured to: receive a first clean low resolution image (102); stochastically corrupt the first clean tow resolution image (102) to generate a corrupted tow resolution image (103); clean the corrupted low resolution image (103) to generate a second clean tow resolution image (105); compare the first clean tow resolution image (102) with the second clean tow resolution image (105); and adapt the image cleaning mode) in dependence on the comparison between the first clean tow resolution image (102) and the second clean tow resolution image (105). By stochastically corrupting the first clean tow resolution image (102), the image cleaning model may be able to team how to clean corrupted tow resolution image (103).</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4302257A1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title APPARATUS AND METHOD FOR IMPROVING PERFORMANCE OF SUPER RESOLUTION FOR PREVIOUSLY UNSEEN IMAGES
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T05%3A53%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=FILIPPOV,%20Alexander%20Nikolaevich&rft.date=2024-01-10&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4302257A1%3C/epo_EVB%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