Video super-resolution reconstruction method based on D3D convolution intra-group fusion network
The invention discloses a video super-resolution reconstruction method based on a D3D convolution intra-group fusion network. The method comprises the following steps: acquiring a low-resolution video sequence to be reconstructed; inputting the low-resolution video sequence to be reconstructed into...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; 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 | JING RUYUN CHEN XIAO |
| description | The invention discloses a video super-resolution reconstruction method based on a D3D convolution intra-group fusion network. The method comprises the following steps: acquiring a low-resolution video sequence to be reconstructed; inputting the low-resolution video sequence to be reconstructed into a tested and trained video super-resolution reconstruction network model; outputting the model to obtain a video super-resolution reconstruction result, namely a high-resolution video sequence; wherein the video super-resolution reconstruction network model comprises a time grouping module, a C3D shallow feature extraction module, a D3D convolution intra-group fusion module, an inter-group attention mechanism module and a reconstruction module. According to the method, the utilization rate of the video frame is improved, the offset vector obtained from the current input feature map can be learned, time and space information can be integrated, and more excellent reconstruction performance is obtained while the time |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115496663A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115496663A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115496663A3</originalsourceid><addsrcrecordid>eNqNysEOATEUheFuLATvUA_QxaQ0sZQZYmUltqM6d2iM3ubeltdXwt7q5D_5xuJ09B2g5ByBFAHjkJPHIAkcBk6U3SfvkK7YybNl6GTpRjeygMeP-5DIqgthjrLP_L4CpCfSbSpGvR0YZt-diPl2c6h3CiK2wNE6KLKt91W1XKyMMXqt_zEvOXQ-MA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Video super-resolution reconstruction method based on D3D convolution intra-group fusion network</title><source>esp@cenet</source><creator>JING RUYUN ; CHEN XIAO</creator><creatorcontrib>JING RUYUN ; CHEN XIAO</creatorcontrib><description>The invention discloses a video super-resolution reconstruction method based on a D3D convolution intra-group fusion network. The method comprises the following steps: acquiring a low-resolution video sequence to be reconstructed; inputting the low-resolution video sequence to be reconstructed into a tested and trained video super-resolution reconstruction network model; outputting the model to obtain a video super-resolution reconstruction result, namely a high-resolution video sequence; wherein the video super-resolution reconstruction network model comprises a time grouping module, a C3D shallow feature extraction module, a D3D convolution intra-group fusion module, an inter-group attention mechanism module and a reconstruction module. According to the method, the utilization rate of the video frame is improved, the offset vector obtained from the current input feature map can be learned, time and space information can be integrated, and more excellent reconstruction performance is obtained while the time</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>2022</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&date=20221220&DB=EPODOC&CC=CN&NR=115496663A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221220&DB=EPODOC&CC=CN&NR=115496663A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JING RUYUN</creatorcontrib><creatorcontrib>CHEN XIAO</creatorcontrib><title>Video super-resolution reconstruction method based on D3D convolution intra-group fusion network</title><description>The invention discloses a video super-resolution reconstruction method based on a D3D convolution intra-group fusion network. The method comprises the following steps: acquiring a low-resolution video sequence to be reconstructed; inputting the low-resolution video sequence to be reconstructed into a tested and trained video super-resolution reconstruction network model; outputting the model to obtain a video super-resolution reconstruction result, namely a high-resolution video sequence; wherein the video super-resolution reconstruction network model comprises a time grouping module, a C3D shallow feature extraction module, a D3D convolution intra-group fusion module, an inter-group attention mechanism module and a reconstruction module. According to the method, the utilization rate of the video frame is improved, the offset vector obtained from the current input feature map can be learned, time and space information can be integrated, and more excellent reconstruction performance is obtained while the time</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNysEOATEUheFuLATvUA_QxaQ0sZQZYmUltqM6d2iM3ubeltdXwt7q5D_5xuJ09B2g5ByBFAHjkJPHIAkcBk6U3SfvkK7YybNl6GTpRjeygMeP-5DIqgthjrLP_L4CpCfSbSpGvR0YZt-diPl2c6h3CiK2wNE6KLKt91W1XKyMMXqt_zEvOXQ-MA</recordid><startdate>20221220</startdate><enddate>20221220</enddate><creator>JING RUYUN</creator><creator>CHEN XIAO</creator><scope>EVB</scope></search><sort><creationdate>20221220</creationdate><title>Video super-resolution reconstruction method based on D3D convolution intra-group fusion network</title><author>JING RUYUN ; CHEN XIAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115496663A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>JING RUYUN</creatorcontrib><creatorcontrib>CHEN XIAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JING RUYUN</au><au>CHEN XIAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Video super-resolution reconstruction method based on D3D convolution intra-group fusion network</title><date>2022-12-20</date><risdate>2022</risdate><abstract>The invention discloses a video super-resolution reconstruction method based on a D3D convolution intra-group fusion network. The method comprises the following steps: acquiring a low-resolution video sequence to be reconstructed; inputting the low-resolution video sequence to be reconstructed into a tested and trained video super-resolution reconstruction network model; outputting the model to obtain a video super-resolution reconstruction result, namely a high-resolution video sequence; wherein the video super-resolution reconstruction network model comprises a time grouping module, a C3D shallow feature extraction module, a D3D convolution intra-group fusion module, an inter-group attention mechanism module and a reconstruction module. According to the method, the utilization rate of the video frame is improved, the offset vector obtained from the current input feature map can be learned, time and space information can be integrated, and more excellent reconstruction performance is obtained while the time</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115496663A |
| 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 reconstruction method based on D3D convolution intra-group fusion network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T12%3A48%3A54IST&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=JING%20RUYUN&rft.date=2022-12-20&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115496663A%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 |