IMAGE PROCESSING DEVICE AND MULTI-FRAME PROCESSING METHOD USING SAME
An image processing apparatus, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: identify, in a previous frame, a prediction sample corresponding to a current sample of a current frame, generat...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; fre ; ger |
| 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 | CHOI, Kwangpyo JIN, Kyonghwan DINH, Quockhanh |
| description | An image processing apparatus, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: identify, in a previous frame, a prediction sample corresponding to a current sample of a current frame, generate a prediction frame for the current frame by changing a sample value of a collocated sample of the previous frame, wherein the collocated sample of the previous frame is collocated with the current sample, according to a sample value of the prediction sample, derive a weight by comparing a sample value of the current sample with the sample value of the prediction sample, apply the weight to a collocated sample of the prediction frame, wherein the collocated sample of the prediction frame is collocated with the current sample, to obtain a weighted prediction frame, and obtain a current output frame by processing the current frame and the weighted prediction frame through a neural network comprising a convolution layer. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4266219A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4266219A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4266219A13</originalsourceid><addsrcrecordid>eNrjZHDx9HV0d1UICPJ3dg0O9vRzV3BxDfN0dlVw9HNR8A31CfHUdQty9EVR4esa4uHvohAK5gQDJXkYWNMSc4pTeaE0N4OCm2uIs4duakF-fGpxQWJyal5qSbxrgImRmZmRoaWjoTERSgDyjys_</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>IMAGE PROCESSING DEVICE AND MULTI-FRAME PROCESSING METHOD USING SAME</title><source>esp@cenet</source><creator>CHOI, Kwangpyo ; JIN, Kyonghwan ; DINH, Quockhanh</creator><creatorcontrib>CHOI, Kwangpyo ; JIN, Kyonghwan ; DINH, Quockhanh</creatorcontrib><description>An image processing apparatus, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: identify, in a previous frame, a prediction sample corresponding to a current sample of a current frame, generate a prediction frame for the current frame by changing a sample value of a collocated sample of the previous frame, wherein the collocated sample of the previous frame is collocated with the current sample, according to a sample value of the prediction sample, derive a weight by comparing a sample value of the current sample with the sample value of the prediction sample, apply the weight to a collocated sample of the prediction frame, wherein the collocated sample of the prediction frame is collocated with the current sample, to obtain a weighted prediction frame, and obtain a current output frame by processing the current frame and the weighted prediction frame through a neural network comprising a convolution layer.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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&date=20231025&DB=EPODOC&CC=EP&NR=4266219A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231025&DB=EPODOC&CC=EP&NR=4266219A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHOI, Kwangpyo</creatorcontrib><creatorcontrib>JIN, Kyonghwan</creatorcontrib><creatorcontrib>DINH, Quockhanh</creatorcontrib><title>IMAGE PROCESSING DEVICE AND MULTI-FRAME PROCESSING METHOD USING SAME</title><description>An image processing apparatus, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: identify, in a previous frame, a prediction sample corresponding to a current sample of a current frame, generate a prediction frame for the current frame by changing a sample value of a collocated sample of the previous frame, wherein the collocated sample of the previous frame is collocated with the current sample, according to a sample value of the prediction sample, derive a weight by comparing a sample value of the current sample with the sample value of the prediction sample, apply the weight to a collocated sample of the prediction frame, wherein the collocated sample of the prediction frame is collocated with the current sample, to obtain a weighted prediction frame, and obtain a current output frame by processing the current frame and the weighted prediction frame through a neural network comprising a convolution layer.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHDx9HV0d1UICPJ3dg0O9vRzV3BxDfN0dlVw9HNR8A31CfHUdQty9EVR4esa4uHvohAK5gQDJXkYWNMSc4pTeaE0N4OCm2uIs4duakF-fGpxQWJyal5qSbxrgImRmZmRoaWjoTERSgDyjys_</recordid><startdate>20231025</startdate><enddate>20231025</enddate><creator>CHOI, Kwangpyo</creator><creator>JIN, Kyonghwan</creator><creator>DINH, Quockhanh</creator><scope>EVB</scope></search><sort><creationdate>20231025</creationdate><title>IMAGE PROCESSING DEVICE AND MULTI-FRAME PROCESSING METHOD USING SAME</title><author>CHOI, Kwangpyo ; JIN, Kyonghwan ; DINH, Quockhanh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4266219A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHOI, Kwangpyo</creatorcontrib><creatorcontrib>JIN, Kyonghwan</creatorcontrib><creatorcontrib>DINH, Quockhanh</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHOI, Kwangpyo</au><au>JIN, Kyonghwan</au><au>DINH, Quockhanh</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>IMAGE PROCESSING DEVICE AND MULTI-FRAME PROCESSING METHOD USING SAME</title><date>2023-10-25</date><risdate>2023</risdate><abstract>An image processing apparatus, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: identify, in a previous frame, a prediction sample corresponding to a current sample of a current frame, generate a prediction frame for the current frame by changing a sample value of a collocated sample of the previous frame, wherein the collocated sample of the previous frame is collocated with the current sample, according to a sample value of the prediction sample, derive a weight by comparing a sample value of the current sample with the sample value of the prediction sample, apply the weight to a collocated sample of the prediction frame, wherein the collocated sample of the prediction frame is collocated with the current sample, to obtain a weighted prediction frame, and obtain a current output frame by processing the current frame and the weighted prediction frame through a neural network comprising a convolution layer.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre ; ger |
| recordid | cdi_epo_espacenet_EP4266219A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | IMAGE PROCESSING DEVICE AND MULTI-FRAME PROCESSING METHOD USING SAME |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T05%3A00%3A52IST&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=CHOI,%20Kwangpyo&rft.date=2023-10-25&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4266219A1%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 |