Video super-resolution recovery method and system based on bidirectional mask video super-resolution network

Video super-resolution recovery method and system based on bidirectional mask video super-resolution network

The invention relates to the technical field of video super-resolution and artificial intelligence algorithms, and discloses a video super-resolution recovery method and system based on a bidirectional mask video super-resolution network, and the method comprises the following specific steps: S1, co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WANG MEILIN, XIAO DI, SONG YEXING, HU KAIHANG, YANG GUOLI, LEE JUN-WOOK, LIANG KAIQING
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
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 WANG MEILIN
XIAO DI
SONG YEXING
HU KAIHANG
YANG GUOLI
LEE JUN-WOOK
LIANG KAIQING
description The invention relates to the technical field of video super-resolution and artificial intelligence algorithms, and discloses a video super-resolution recovery method and system based on a bidirectional mask video super-resolution network, and the method comprises the following specific steps: S1, constructing the bidirectional mask video super-resolution network of a random mask; degenerating the training video data set to obtain a low-resolution video data set; s2, inputting the low-resolution video data into a bidirectional mask video super-resolution network of a random mask, and carrying out Switch White based on a dark channel; s3, performing bidirectional video masking on the processed video data; s4, recovering the video features into a high-resolution video to obtain a high-resolution video data set; s5, calculating loss, and training a bidirectional mask video super-resolution network; and S6, carrying out super-resolution recovery on the real video. The method solves the problems of low training spe
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117094893A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117094893A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117094893A3</originalsourceid><addsrcrecordid>eNqNzLEKwjAURuEuDqK-w_UBCpYK2lGK4uQkriVtfmlo2hty00rf3giODk5n-TjLxD6MBpOMDj71ELZjMDyQR8MT_Ew9Qsua1KBJZgnoqVYCTdHURpvoPl5Z6pV0NP2-DQgv9t06WTyVFWy-XSXby_leXlM4riBONYiyKm9ZdtgV-2ORn_J_zBvAF0MI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Video super-resolution recovery method and system based on bidirectional mask video super-resolution network</title><source>esp@cenet</source><creator>WANG MEILIN ; XIAO DI ; SONG YEXING ; HU KAIHANG ; YANG GUOLI ; LEE JUN-WOOK ; LIANG KAIQING</creator><creatorcontrib>WANG MEILIN ; XIAO DI ; SONG YEXING ; HU KAIHANG ; YANG GUOLI ; LEE JUN-WOOK ; LIANG KAIQING</creatorcontrib><description>The invention relates to the technical field of video super-resolution and artificial intelligence algorithms, and discloses a video super-resolution recovery method and system based on a bidirectional mask video super-resolution network, and the method comprises the following specific steps: S1, constructing the bidirectional mask video super-resolution network of a random mask; degenerating the training video data set to obtain a low-resolution video data set; s2, inputting the low-resolution video data into a bidirectional mask video super-resolution network of a random mask, and carrying out Switch White based on a dark channel; s3, performing bidirectional video masking on the processed video data; s4, recovering the video features into a high-resolution video to obtain a high-resolution video data set; s5, calculating loss, and training a bidirectional mask video super-resolution network; and S6, carrying out super-resolution recovery on the real video. The method solves the problems of low training spe</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2023</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=20231121&amp;DB=EPODOC&amp;CC=CN&amp;NR=117094893A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76419</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20231121&amp;DB=EPODOC&amp;CC=CN&amp;NR=117094893A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG MEILIN</creatorcontrib><creatorcontrib>XIAO DI</creatorcontrib><creatorcontrib>SONG YEXING</creatorcontrib><creatorcontrib>HU KAIHANG</creatorcontrib><creatorcontrib>YANG GUOLI</creatorcontrib><creatorcontrib>LEE JUN-WOOK</creatorcontrib><creatorcontrib>LIANG KAIQING</creatorcontrib><title>Video super-resolution recovery method and system based on bidirectional mask video super-resolution network</title><description>The invention relates to the technical field of video super-resolution and artificial intelligence algorithms, and discloses a video super-resolution recovery method and system based on a bidirectional mask video super-resolution network, and the method comprises the following specific steps: S1, constructing the bidirectional mask video super-resolution network of a random mask; degenerating the training video data set to obtain a low-resolution video data set; s2, inputting the low-resolution video data into a bidirectional mask video super-resolution network of a random mask, and carrying out Switch White based on a dark channel; s3, performing bidirectional video masking on the processed video data; s4, recovering the video features into a high-resolution video to obtain a high-resolution video data set; s5, calculating loss, and training a bidirectional mask video super-resolution network; and S6, carrying out super-resolution recovery on the real video. The method solves the problems of low training spe</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNzLEKwjAURuEuDqK-w_UBCpYK2lGK4uQkriVtfmlo2hty00rf3giODk5n-TjLxD6MBpOMDj71ELZjMDyQR8MT_Ew9Qsua1KBJZgnoqVYCTdHURpvoPl5Z6pV0NP2-DQgv9t06WTyVFWy-XSXby_leXlM4riBONYiyKm9ZdtgV-2ORn_J_zBvAF0MI</recordid><startdate>20231121</startdate><enddate>20231121</enddate><creator>WANG MEILIN</creator><creator>XIAO DI</creator><creator>SONG YEXING</creator><creator>HU KAIHANG</creator><creator>YANG GUOLI</creator><creator>LEE JUN-WOOK</creator><creator>LIANG KAIQING</creator><scope>EVB</scope></search><sort><creationdate>20231121</creationdate><title>Video super-resolution recovery method and system based on bidirectional mask video super-resolution network</title><author>WANG MEILIN ; XIAO DI ; SONG YEXING ; HU KAIHANG ; YANG GUOLI ; LEE JUN-WOOK ; LIANG KAIQING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117094893A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG MEILIN</creatorcontrib><creatorcontrib>XIAO DI</creatorcontrib><creatorcontrib>SONG YEXING</creatorcontrib><creatorcontrib>HU KAIHANG</creatorcontrib><creatorcontrib>YANG GUOLI</creatorcontrib><creatorcontrib>LEE JUN-WOOK</creatorcontrib><creatorcontrib>LIANG KAIQING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG MEILIN</au><au>XIAO DI</au><au>SONG YEXING</au><au>HU KAIHANG</au><au>YANG GUOLI</au><au>LEE JUN-WOOK</au><au>LIANG KAIQING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Video super-resolution recovery method and system based on bidirectional mask video super-resolution network</title><date>2023-11-21</date><risdate>2023</risdate><abstract>The invention relates to the technical field of video super-resolution and artificial intelligence algorithms, and discloses a video super-resolution recovery method and system based on a bidirectional mask video super-resolution network, and the method comprises the following specific steps: S1, constructing the bidirectional mask video super-resolution network of a random mask; degenerating the training video data set to obtain a low-resolution video data set; s2, inputting the low-resolution video data into a bidirectional mask video super-resolution network of a random mask, and carrying out Switch White based on a dark channel; s3, performing bidirectional video masking on the processed video data; s4, recovering the video features into a high-resolution video to obtain a high-resolution video data set; s5, calculating loss, and training a bidirectional mask video super-resolution network; and S6, carrying out super-resolution recovery on the real video. The method solves the problems of low training spe</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117094893A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Video super-resolution recovery method and system based on bidirectional mask video super-resolution network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T05%3A25%3A53IST&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=WANG%20MEILIN&rft.date=2023-11-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117094893A%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