ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE
The present disclosure relates to the field of image processing. An image processing unit comprises: an encoder configured to receive blurry image data and to generate the global feature map of an image; a combination unit configured to combine the global feature map and blur information; a decoder...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; kor |
| 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 | ZAVALISHIN SERGEY STANISLAVOVICH DOROKHOV EVGENY ANDREEVICH ANISIMOVSKIY VALERY VALERIEVICH PENKIN MAKSIM ALEXANDROVICH GRUZDEV ALEKSEI MIKHAILOVICH |
| description | The present disclosure relates to the field of image processing. An image processing unit comprises: an encoder configured to receive blurry image data and to generate the global feature map of an image; a combination unit configured to combine the global feature map and blur information; a decoder configured to generate a feature tensor and weight tensors; a recurrent refinement module configured to perform recurrent feature filtering; and an image recomposition module configured to recompose a deblurred image, wherein the image processing unit is configured to estimate the global shift of an image and to activate or inactivate the recurrent refinement module based on the estimation. The technical result is composed by a decrease in the complexity of image processing, increase in the speed of image processing and improvement in the quality of the resulting image.
본 개시는 이미지 프로세싱의 분야에 관한 것이다. 이미지 프로세싱 유닛은, 블러리 이미지 데이터를 수신하고, 이미지의 전역적 특징 맵을 생성하도록 구성된 인코더, 전역적 특징 맵과 블러 정보를 병합하도록 구성된 병합 유닛, 특징 텐서 및 가중치 텐서들을 생성하도록 구성된 디코더, 순환 특징 필터링을 수행하도록 구성된 순환 리파인먼트 모듈 및 디블러링된 이미지를 재구성하도록 구성된 이미지 재구성 모듈을 포함하며, 여기서, 이미지 프로세싱 유닛은 이미지 전역적 시프트를 추정하고, 그 추정에 기반하여 순환 리파인먼트 모듈을 활성화 또는 비활성화하도록 구성된다. 기술적 결과는 이미지 프로세싱 복잡성의 감소, 이미지 프로세싱의 속도의 증가 및 결과 이미지의 품질의 개선으로 구성된다. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20220003946A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20220003946A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20220003946A3</originalsourceid><addsrcrecordid>eNrjZLB19XF1Dgny9_N0VnBxDfN0dlVw9HNRcPb3Awr6-Hj6uSv4uoZ4-Lso-LspYKjlYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXx3kFGBkZGBgYGxpYmZo7GxKkCAL_iKnw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE</title><source>esp@cenet</source><creator>ZAVALISHIN SERGEY STANISLAVOVICH ; DOROKHOV EVGENY ANDREEVICH ; ANISIMOVSKIY VALERY VALERIEVICH ; PENKIN MAKSIM ALEXANDROVICH ; GRUZDEV ALEKSEI MIKHAILOVICH</creator><creatorcontrib>ZAVALISHIN SERGEY STANISLAVOVICH ; DOROKHOV EVGENY ANDREEVICH ; ANISIMOVSKIY VALERY VALERIEVICH ; PENKIN MAKSIM ALEXANDROVICH ; GRUZDEV ALEKSEI MIKHAILOVICH</creatorcontrib><description>The present disclosure relates to the field of image processing. An image processing unit comprises: an encoder configured to receive blurry image data and to generate the global feature map of an image; a combination unit configured to combine the global feature map and blur information; a decoder configured to generate a feature tensor and weight tensors; a recurrent refinement module configured to perform recurrent feature filtering; and an image recomposition module configured to recompose a deblurred image, wherein the image processing unit is configured to estimate the global shift of an image and to activate or inactivate the recurrent refinement module based on the estimation. The technical result is composed by a decrease in the complexity of image processing, increase in the speed of image processing and improvement in the quality of the resulting image.
본 개시는 이미지 프로세싱의 분야에 관한 것이다. 이미지 프로세싱 유닛은, 블러리 이미지 데이터를 수신하고, 이미지의 전역적 특징 맵을 생성하도록 구성된 인코더, 전역적 특징 맵과 블러 정보를 병합하도록 구성된 병합 유닛, 특징 텐서 및 가중치 텐서들을 생성하도록 구성된 디코더, 순환 특징 필터링을 수행하도록 구성된 순환 리파인먼트 모듈 및 디블러링된 이미지를 재구성하도록 구성된 이미지 재구성 모듈을 포함하며, 여기서, 이미지 프로세싱 유닛은 이미지 전역적 시프트를 추정하고, 그 추정에 기반하여 순환 리파인먼트 모듈을 활성화 또는 비활성화하도록 구성된다. 기술적 결과는 이미지 프로세싱 복잡성의 감소, 이미지 프로세싱의 속도의 증가 및 결과 이미지의 품질의 개선으로 구성된다.</description><language>eng ; kor</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=20220111&DB=EPODOC&CC=KR&NR=20220003946A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220111&DB=EPODOC&CC=KR&NR=20220003946A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZAVALISHIN SERGEY STANISLAVOVICH</creatorcontrib><creatorcontrib>DOROKHOV EVGENY ANDREEVICH</creatorcontrib><creatorcontrib>ANISIMOVSKIY VALERY VALERIEVICH</creatorcontrib><creatorcontrib>PENKIN MAKSIM ALEXANDROVICH</creatorcontrib><creatorcontrib>GRUZDEV ALEKSEI MIKHAILOVICH</creatorcontrib><title>ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE</title><description>The present disclosure relates to the field of image processing. An image processing unit comprises: an encoder configured to receive blurry image data and to generate the global feature map of an image; a combination unit configured to combine the global feature map and blur information; a decoder configured to generate a feature tensor and weight tensors; a recurrent refinement module configured to perform recurrent feature filtering; and an image recomposition module configured to recompose a deblurred image, wherein the image processing unit is configured to estimate the global shift of an image and to activate or inactivate the recurrent refinement module based on the estimation. The technical result is composed by a decrease in the complexity of image processing, increase in the speed of image processing and improvement in the quality of the resulting image.
본 개시는 이미지 프로세싱의 분야에 관한 것이다. 이미지 프로세싱 유닛은, 블러리 이미지 데이터를 수신하고, 이미지의 전역적 특징 맵을 생성하도록 구성된 인코더, 전역적 특징 맵과 블러 정보를 병합하도록 구성된 병합 유닛, 특징 텐서 및 가중치 텐서들을 생성하도록 구성된 디코더, 순환 특징 필터링을 수행하도록 구성된 순환 리파인먼트 모듈 및 디블러링된 이미지를 재구성하도록 구성된 이미지 재구성 모듈을 포함하며, 여기서, 이미지 프로세싱 유닛은 이미지 전역적 시프트를 추정하고, 그 추정에 기반하여 순환 리파인먼트 모듈을 활성화 또는 비활성화하도록 구성된다. 기술적 결과는 이미지 프로세싱 복잡성의 감소, 이미지 프로세싱의 속도의 증가 및 결과 이미지의 품질의 개선으로 구성된다.</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>eNrjZLB19XF1Dgny9_N0VnBxDfN0dlVw9HNRcPb3Awr6-Hj6uSv4uoZ4-Lso-LspYKjlYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXx3kFGBkZGBgYGxpYmZo7GxKkCAL_iKnw</recordid><startdate>20220111</startdate><enddate>20220111</enddate><creator>ZAVALISHIN SERGEY STANISLAVOVICH</creator><creator>DOROKHOV EVGENY ANDREEVICH</creator><creator>ANISIMOVSKIY VALERY VALERIEVICH</creator><creator>PENKIN MAKSIM ALEXANDROVICH</creator><creator>GRUZDEV ALEKSEI MIKHAILOVICH</creator><scope>EVB</scope></search><sort><creationdate>20220111</creationdate><title>ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE</title><author>ZAVALISHIN SERGEY STANISLAVOVICH ; DOROKHOV EVGENY ANDREEVICH ; ANISIMOVSKIY VALERY VALERIEVICH ; PENKIN MAKSIM ALEXANDROVICH ; GRUZDEV ALEKSEI MIKHAILOVICH</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20220003946A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</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>ZAVALISHIN SERGEY STANISLAVOVICH</creatorcontrib><creatorcontrib>DOROKHOV EVGENY ANDREEVICH</creatorcontrib><creatorcontrib>ANISIMOVSKIY VALERY VALERIEVICH</creatorcontrib><creatorcontrib>PENKIN MAKSIM ALEXANDROVICH</creatorcontrib><creatorcontrib>GRUZDEV ALEKSEI MIKHAILOVICH</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZAVALISHIN SERGEY STANISLAVOVICH</au><au>DOROKHOV EVGENY ANDREEVICH</au><au>ANISIMOVSKIY VALERY VALERIEVICH</au><au>PENKIN MAKSIM ALEXANDROVICH</au><au>GRUZDEV ALEKSEI MIKHAILOVICH</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE</title><date>2022-01-11</date><risdate>2022</risdate><abstract>The present disclosure relates to the field of image processing. An image processing unit comprises: an encoder configured to receive blurry image data and to generate the global feature map of an image; a combination unit configured to combine the global feature map and blur information; a decoder configured to generate a feature tensor and weight tensors; a recurrent refinement module configured to perform recurrent feature filtering; and an image recomposition module configured to recompose a deblurred image, wherein the image processing unit is configured to estimate the global shift of an image and to activate or inactivate the recurrent refinement module based on the estimation. The technical result is composed by a decrease in the complexity of image processing, increase in the speed of image processing and improvement in the quality of the resulting image.
본 개시는 이미지 프로세싱의 분야에 관한 것이다. 이미지 프로세싱 유닛은, 블러리 이미지 데이터를 수신하고, 이미지의 전역적 특징 맵을 생성하도록 구성된 인코더, 전역적 특징 맵과 블러 정보를 병합하도록 구성된 병합 유닛, 특징 텐서 및 가중치 텐서들을 생성하도록 구성된 디코더, 순환 특징 필터링을 수행하도록 구성된 순환 리파인먼트 모듈 및 디블러링된 이미지를 재구성하도록 구성된 이미지 재구성 모듈을 포함하며, 여기서, 이미지 프로세싱 유닛은 이미지 전역적 시프트를 추정하고, 그 추정에 기반하여 순환 리파인먼트 모듈을 활성화 또는 비활성화하도록 구성된다. 기술적 결과는 이미지 프로세싱 복잡성의 감소, 이미지 프로세싱의 속도의 증가 및 결과 이미지의 품질의 개선으로 구성된다.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; kor |
| recordid | cdi_epo_espacenet_KR20220003946A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T02%3A47%3A22IST&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=ZAVALISHIN%20SERGEY%20STANISLAVOVICH&rft.date=2022-01-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20220003946A%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 |