Image enhancement method and device fusing wavelet transform and attention mechanism
The invention provides an image enhancement method and device fusing wavelet transform and an attention mechanism, and the method comprises the steps: inputting a target image into a feature extraction branch model in an enhancement model, and obtaining a plurality of first feature maps of different...
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 | XU JINGZHAO YAN DONGMING WU TIERU QUAN WEIZE YUAN MENGKE |
| description | The invention provides an image enhancement method and device fusing wavelet transform and an attention mechanism, and the method comprises the steps: inputting a target image into a feature extraction branch model in an enhancement model, and obtaining a plurality of first feature maps of different scales of the target image; inputting the target image into a first down-sampling module of an image enhancement branch model in the enhancement model to obtain a second feature map of the target image; inputting the second feature map and the first feature map into a first up-sampling module of an image enhancement branch model to obtain a third feature map of the target image; the first up-sampling module and the first down-sampling module are both fused with wavelet transform and an attention mechanism; and inputting the third feature map of the target image into a third output layer of the image enhancement branch model to obtain an enhanced image of the target image. According to the method, the wavelet trans |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115170410A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115170410A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115170410A3</originalsourceid><addsrcrecordid>eNqNjLEKwkAQBdNYiPoP6wcIOVSsQ1C0sUoflruX5CC3F3Jr_H0P8QOsppmZddE8AvcgyMBiESBKATpERyyOHBZvQd0reenpzQtGKOnMkro4h6_DqrnyUXJo88WnsC1WHY8Jux83xf52ber7AVNskSa2EGhbP405m0t5MmV1_Mf5ALUwOQ4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Image enhancement method and device fusing wavelet transform and attention mechanism</title><source>esp@cenet</source><creator>XU JINGZHAO ; YAN DONGMING ; WU TIERU ; QUAN WEIZE ; YUAN MENGKE</creator><creatorcontrib>XU JINGZHAO ; YAN DONGMING ; WU TIERU ; QUAN WEIZE ; YUAN MENGKE</creatorcontrib><description>The invention provides an image enhancement method and device fusing wavelet transform and an attention mechanism, and the method comprises the steps: inputting a target image into a feature extraction branch model in an enhancement model, and obtaining a plurality of first feature maps of different scales of the target image; inputting the target image into a first down-sampling module of an image enhancement branch model in the enhancement model to obtain a second feature map of the target image; inputting the second feature map and the first feature map into a first up-sampling module of an image enhancement branch model to obtain a third feature map of the target image; the first up-sampling module and the first down-sampling module are both fused with wavelet transform and an attention mechanism; and inputting the third feature map of the target image into a third output layer of the image enhancement branch model to obtain an enhanced image of the target image. According to the method, the wavelet trans</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=20221011&DB=EPODOC&CC=CN&NR=115170410A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76418</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221011&DB=EPODOC&CC=CN&NR=115170410A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>XU JINGZHAO</creatorcontrib><creatorcontrib>YAN DONGMING</creatorcontrib><creatorcontrib>WU TIERU</creatorcontrib><creatorcontrib>QUAN WEIZE</creatorcontrib><creatorcontrib>YUAN MENGKE</creatorcontrib><title>Image enhancement method and device fusing wavelet transform and attention mechanism</title><description>The invention provides an image enhancement method and device fusing wavelet transform and an attention mechanism, and the method comprises the steps: inputting a target image into a feature extraction branch model in an enhancement model, and obtaining a plurality of first feature maps of different scales of the target image; inputting the target image into a first down-sampling module of an image enhancement branch model in the enhancement model to obtain a second feature map of the target image; inputting the second feature map and the first feature map into a first up-sampling module of an image enhancement branch model to obtain a third feature map of the target image; the first up-sampling module and the first down-sampling module are both fused with wavelet transform and an attention mechanism; and inputting the third feature map of the target image into a third output layer of the image enhancement branch model to obtain an enhanced image of the target image. According to the method, the wavelet trans</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>eNqNjLEKwkAQBdNYiPoP6wcIOVSsQ1C0sUoflruX5CC3F3Jr_H0P8QOsppmZddE8AvcgyMBiESBKATpERyyOHBZvQd0reenpzQtGKOnMkro4h6_DqrnyUXJo88WnsC1WHY8Jux83xf52ber7AVNskSa2EGhbP405m0t5MmV1_Mf5ALUwOQ4</recordid><startdate>20221011</startdate><enddate>20221011</enddate><creator>XU JINGZHAO</creator><creator>YAN DONGMING</creator><creator>WU TIERU</creator><creator>QUAN WEIZE</creator><creator>YUAN MENGKE</creator><scope>EVB</scope></search><sort><creationdate>20221011</creationdate><title>Image enhancement method and device fusing wavelet transform and attention mechanism</title><author>XU JINGZHAO ; YAN DONGMING ; WU TIERU ; QUAN WEIZE ; YUAN MENGKE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115170410A3</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>XU JINGZHAO</creatorcontrib><creatorcontrib>YAN DONGMING</creatorcontrib><creatorcontrib>WU TIERU</creatorcontrib><creatorcontrib>QUAN WEIZE</creatorcontrib><creatorcontrib>YUAN MENGKE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>XU JINGZHAO</au><au>YAN DONGMING</au><au>WU TIERU</au><au>QUAN WEIZE</au><au>YUAN MENGKE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Image enhancement method and device fusing wavelet transform and attention mechanism</title><date>2022-10-11</date><risdate>2022</risdate><abstract>The invention provides an image enhancement method and device fusing wavelet transform and an attention mechanism, and the method comprises the steps: inputting a target image into a feature extraction branch model in an enhancement model, and obtaining a plurality of first feature maps of different scales of the target image; inputting the target image into a first down-sampling module of an image enhancement branch model in the enhancement model to obtain a second feature map of the target image; inputting the second feature map and the first feature map into a first up-sampling module of an image enhancement branch model to obtain a third feature map of the target image; the first up-sampling module and the first down-sampling module are both fused with wavelet transform and an attention mechanism; and inputting the third feature map of the target image into a third output layer of the image enhancement branch model to obtain an enhanced image of the target image. According to the method, the wavelet trans</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115170410A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Image enhancement method and device fusing wavelet transform and attention mechanism |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T14%3A46%3A37IST&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=XU%20JINGZHAO&rft.date=2022-10-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115170410A%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 |