Method and apparatus for training neural network model for enhancing image detail

A neural network model training apparatus for enhancing image detail is provided. The apparatus includes a memory and at least one processor configured to obtain a low quality input image patch and a high quality input image patch, obtain a low quality output image patch by inputting the low quality...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shcherbinin, Andrei Yurievich, Biryulin, Pavel Igorevich, Anisimovskiy, Valery Valerievich
Format: Patent
Sprache: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 Shcherbinin, Andrei Yurievich
Biryulin, Pavel Igorevich
Anisimovskiy, Valery Valerievich
description A neural network model training apparatus for enhancing image detail is provided. The apparatus includes a memory and at least one processor configured to obtain a low quality input image patch and a high quality input image patch, obtain a low quality output image patch by inputting the low quality input image patch to a first neural network model, obtain a high quality output image patch by inputting the high quality input image patch to a second neural network model, and train the first neural network model based on a loss function set to reduce a difference between the low quality output image patch and the high quality input image patch, and a difference between the high quality output image patch and the high quality input image patch. The second neural network model is identical to the first neural network model.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11521011B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11521011B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11521011B23</originalsourceid><addsrcrecordid>eNrjZAj0TS3JyE9RSMwD4oKCxKLEktJihbT8IoWSosTMvMy8dIW81NKixBwgVVKeX5StkJufkpoDVpGal5GYlwxSkpmbmJ6qkJJakpiZw8PAmpaYU5zKC6W5GRTdXEOcPXRTC_LjU4sLEpNTgUbFhwYbGpoaGRoYGjoZGROjBgDZ-ze2</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method and apparatus for training neural network model for enhancing image detail</title><source>esp@cenet</source><creator>Shcherbinin, Andrei Yurievich ; Biryulin, Pavel Igorevich ; Anisimovskiy, Valery Valerievich</creator><creatorcontrib>Shcherbinin, Andrei Yurievich ; Biryulin, Pavel Igorevich ; Anisimovskiy, Valery Valerievich</creatorcontrib><description>A neural network model training apparatus for enhancing image detail is provided. The apparatus includes a memory and at least one processor configured to obtain a low quality input image patch and a high quality input image patch, obtain a low quality output image patch by inputting the low quality input image patch to a first neural network model, obtain a high quality output image patch by inputting the high quality input image patch to a second neural network model, and train the first neural network model based on a loss function set to reduce a difference between the low quality output image patch and the high quality input image patch, and a difference between the high quality output image patch and the high quality input image patch. The second neural network model is identical to the first neural network model.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</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&amp;date=20221206&amp;DB=EPODOC&amp;CC=US&amp;NR=11521011B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20221206&amp;DB=EPODOC&amp;CC=US&amp;NR=11521011B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Shcherbinin, Andrei Yurievich</creatorcontrib><creatorcontrib>Biryulin, Pavel Igorevich</creatorcontrib><creatorcontrib>Anisimovskiy, Valery Valerievich</creatorcontrib><title>Method and apparatus for training neural network model for enhancing image detail</title><description>A neural network model training apparatus for enhancing image detail is provided. The apparatus includes a memory and at least one processor configured to obtain a low quality input image patch and a high quality input image patch, obtain a low quality output image patch by inputting the low quality input image patch to a first neural network model, obtain a high quality output image patch by inputting the high quality input image patch to a second neural network model, and train the first neural network model based on a loss function set to reduce a difference between the low quality output image patch and the high quality input image patch, and a difference between the high quality output image patch and the high quality input image patch. The second neural network model is identical to the first neural network model.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZAj0TS3JyE9RSMwD4oKCxKLEktJihbT8IoWSosTMvMy8dIW81NKixBwgVVKeX5StkJufkpoDVpGal5GYlwxSkpmbmJ6qkJJakpiZw8PAmpaYU5zKC6W5GRTdXEOcPXRTC_LjU4sLEpNTgUbFhwYbGpoaGRoYGjoZGROjBgDZ-ze2</recordid><startdate>20221206</startdate><enddate>20221206</enddate><creator>Shcherbinin, Andrei Yurievich</creator><creator>Biryulin, Pavel Igorevich</creator><creator>Anisimovskiy, Valery Valerievich</creator><scope>EVB</scope></search><sort><creationdate>20221206</creationdate><title>Method and apparatus for training neural network model for enhancing image detail</title><author>Shcherbinin, Andrei Yurievich ; Biryulin, Pavel Igorevich ; Anisimovskiy, Valery Valerievich</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11521011B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>Shcherbinin, Andrei Yurievich</creatorcontrib><creatorcontrib>Biryulin, Pavel Igorevich</creatorcontrib><creatorcontrib>Anisimovskiy, Valery Valerievich</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Shcherbinin, Andrei Yurievich</au><au>Biryulin, Pavel Igorevich</au><au>Anisimovskiy, Valery Valerievich</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method and apparatus for training neural network model for enhancing image detail</title><date>2022-12-06</date><risdate>2022</risdate><abstract>A neural network model training apparatus for enhancing image detail is provided. The apparatus includes a memory and at least one processor configured to obtain a low quality input image patch and a high quality input image patch, obtain a low quality output image patch by inputting the low quality input image patch to a first neural network model, obtain a high quality output image patch by inputting the high quality input image patch to a second neural network model, and train the first neural network model based on a loss function set to reduce a difference between the low quality output image patch and the high quality input image patch, and a difference between the high quality output image patch and the high quality input image patch. The second neural network model is identical to the first neural network model.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11521011B2
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
title Method and apparatus for training neural network model for enhancing image detail
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A34%3A15IST&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=Shcherbinin,%20Andrei%20Yurievich&rft.date=2022-12-06&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11521011B2%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