Lightweight deep learning compression imaging method and device based on physical inspiration
The invention relates to a lightweight deep learning compression imaging method and device based on physical inspiration. The method comprises the following steps: constructing a compressed holographic sensing model; acquiring low-dimensional diffracted intensity by using a compressed holographic se...
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 | ZHANG CHENG CHENG HONG ZHANG QUANBING HAN PENG SHEN CHUAN SHI JISEN WEI SUI ZHOU HAO |
| description | The invention relates to a lightweight deep learning compression imaging method and device based on physical inspiration. The method comprises the following steps: constructing a compressed holographic sensing model; acquiring low-dimensional diffracted intensity by using a compressed holographic sensing model, constructing a computational imaging frame by using a computational super-resolution reconstruction method, and recovering complex-value amplitude from the low-dimensional diffracted intensity by using the computational imaging frame; respectively constructing a lightweight calculation imaging framework and a distance generation network based on an LIST layer; determining a lightweight deep learning compression holographic imaging model by using a lightweight calculation imaging framework and the distance generation network; and carrying out compressed holographic imaging by using the lightweight deep learning compressed holographic imaging model. The method disclosed by the invention consumes less tim |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117853336A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117853336A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117853336A3</originalsourceid><addsrcrecordid>eNqNy70KwkAQBOA0FqK-w_oAFuHwpw1BsRArWwnr3ZhbSO6O7KH49ibgA9jMwPDNvLhfpPX5jSnJAYk68BAktGRjnwaoSgwkPbfT1iP76IiDG_FLLOjBCkcjSf6jYrkjCZpk4Dz-lsXsyZ1i9etFsT4db_V5gxQbaGKLgNzU17LcH7bGmF1l_jFfOSY8tw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Lightweight deep learning compression imaging method and device based on physical inspiration</title><source>esp@cenet</source><creator>ZHANG CHENG ; CHENG HONG ; ZHANG QUANBING ; HAN PENG ; SHEN CHUAN ; SHI JISEN ; WEI SUI ; ZHOU HAO</creator><creatorcontrib>ZHANG CHENG ; CHENG HONG ; ZHANG QUANBING ; HAN PENG ; SHEN CHUAN ; SHI JISEN ; WEI SUI ; ZHOU HAO</creatorcontrib><description>The invention relates to a lightweight deep learning compression imaging method and device based on physical inspiration. The method comprises the following steps: constructing a compressed holographic sensing model; acquiring low-dimensional diffracted intensity by using a compressed holographic sensing model, constructing a computational imaging frame by using a computational super-resolution reconstruction method, and recovering complex-value amplitude from the low-dimensional diffracted intensity by using the computational imaging frame; respectively constructing a lightweight calculation imaging framework and a distance generation network based on an LIST layer; determining a lightweight deep learning compression holographic imaging model by using a lightweight calculation imaging framework and the distance generation network; and carrying out compressed holographic imaging by using the lightweight deep learning compressed holographic imaging model. The method disclosed by the invention consumes less tim</description><language>chi ; eng</language><subject>CALCULATING ; CINEMATOGRAPHY ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTROGRAPHY ; HOLOGRAPHIC PROCESSES OR APPARATUS ; HOLOGRAPHY ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHOTOGRAPHY ; 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&date=20240409&DB=EPODOC&CC=CN&NR=117853336A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240409&DB=EPODOC&CC=CN&NR=117853336A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG CHENG</creatorcontrib><creatorcontrib>CHENG HONG</creatorcontrib><creatorcontrib>ZHANG QUANBING</creatorcontrib><creatorcontrib>HAN PENG</creatorcontrib><creatorcontrib>SHEN CHUAN</creatorcontrib><creatorcontrib>SHI JISEN</creatorcontrib><creatorcontrib>WEI SUI</creatorcontrib><creatorcontrib>ZHOU HAO</creatorcontrib><title>Lightweight deep learning compression imaging method and device based on physical inspiration</title><description>The invention relates to a lightweight deep learning compression imaging method and device based on physical inspiration. The method comprises the following steps: constructing a compressed holographic sensing model; acquiring low-dimensional diffracted intensity by using a compressed holographic sensing model, constructing a computational imaging frame by using a computational super-resolution reconstruction method, and recovering complex-value amplitude from the low-dimensional diffracted intensity by using the computational imaging frame; respectively constructing a lightweight calculation imaging framework and a distance generation network based on an LIST layer; determining a lightweight deep learning compression holographic imaging model by using a lightweight calculation imaging framework and the distance generation network; and carrying out compressed holographic imaging by using the lightweight deep learning compressed holographic imaging model. The method disclosed by the invention consumes less tim</description><subject>CALCULATING</subject><subject>CINEMATOGRAPHY</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTROGRAPHY</subject><subject>HOLOGRAPHIC PROCESSES OR APPARATUS</subject><subject>HOLOGRAPHY</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHOTOGRAPHY</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNy70KwkAQBOA0FqK-w_oAFuHwpw1BsRArWwnr3ZhbSO6O7KH49ibgA9jMwPDNvLhfpPX5jSnJAYk68BAktGRjnwaoSgwkPbfT1iP76IiDG_FLLOjBCkcjSf6jYrkjCZpk4Dz-lsXsyZ1i9etFsT4db_V5gxQbaGKLgNzU17LcH7bGmF1l_jFfOSY8tw</recordid><startdate>20240409</startdate><enddate>20240409</enddate><creator>ZHANG CHENG</creator><creator>CHENG HONG</creator><creator>ZHANG QUANBING</creator><creator>HAN PENG</creator><creator>SHEN CHUAN</creator><creator>SHI JISEN</creator><creator>WEI SUI</creator><creator>ZHOU HAO</creator><scope>EVB</scope></search><sort><creationdate>20240409</creationdate><title>Lightweight deep learning compression imaging method and device based on physical inspiration</title><author>ZHANG CHENG ; CHENG HONG ; ZHANG QUANBING ; HAN PENG ; SHEN CHUAN ; SHI JISEN ; WEI SUI ; ZHOU HAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117853336A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>CINEMATOGRAPHY</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTROGRAPHY</topic><topic>HOLOGRAPHIC PROCESSES OR APPARATUS</topic><topic>HOLOGRAPHY</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHOTOGRAPHY</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHANG CHENG</creatorcontrib><creatorcontrib>CHENG HONG</creatorcontrib><creatorcontrib>ZHANG QUANBING</creatorcontrib><creatorcontrib>HAN PENG</creatorcontrib><creatorcontrib>SHEN CHUAN</creatorcontrib><creatorcontrib>SHI JISEN</creatorcontrib><creatorcontrib>WEI SUI</creatorcontrib><creatorcontrib>ZHOU HAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG CHENG</au><au>CHENG HONG</au><au>ZHANG QUANBING</au><au>HAN PENG</au><au>SHEN CHUAN</au><au>SHI JISEN</au><au>WEI SUI</au><au>ZHOU HAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Lightweight deep learning compression imaging method and device based on physical inspiration</title><date>2024-04-09</date><risdate>2024</risdate><abstract>The invention relates to a lightweight deep learning compression imaging method and device based on physical inspiration. The method comprises the following steps: constructing a compressed holographic sensing model; acquiring low-dimensional diffracted intensity by using a compressed holographic sensing model, constructing a computational imaging frame by using a computational super-resolution reconstruction method, and recovering complex-value amplitude from the low-dimensional diffracted intensity by using the computational imaging frame; respectively constructing a lightweight calculation imaging framework and a distance generation network based on an LIST layer; determining a lightweight deep learning compression holographic imaging model by using a lightweight calculation imaging framework and the distance generation network; and carrying out compressed holographic imaging by using the lightweight deep learning compressed holographic imaging model. The method disclosed by the invention consumes less tim</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117853336A |
| source | esp@cenet |
| subjects | CALCULATING CINEMATOGRAPHY COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTROGRAPHY HOLOGRAPHIC PROCESSES OR APPARATUS HOLOGRAPHY IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHOTOGRAPHY PHYSICS |
| title | Lightweight deep learning compression imaging method and device based on physical inspiration |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T05%3A31%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=ZHANG%20CHENG&rft.date=2024-04-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117853336A%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 |