LDR HDR Method and Apparatus for Providing an HDR Environment Map from an LDR Image Based on Deep Learning

Disclosed is a method for providing a high dynamic range (HDR) environment map from a low dynamic range (LDR) image based on deep learning. The method comprises the steps of: inputting an LDR image into a first deep neural network (DNN), and outputting an LDR environment map; and inputting the LDR e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LEE JI WON, YOO JUNG EUN, SEO KWANG GYOON, NOH JUN YONG, LEE HA NUI
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 LEE JI WON
YOO JUNG EUN
SEO KWANG GYOON
NOH JUN YONG
LEE HA NUI
description Disclosed is a method for providing a high dynamic range (HDR) environment map from a low dynamic range (LDR) image based on deep learning. The method comprises the steps of: inputting an LDR image into a first deep neural network (DNN), and outputting an LDR environment map; and inputting the LDR environment map into a second DNN to output an HDR environment map. The LDR environment map includes information indicating the location and intensity of a light source in the LDR image and information on a color of the LDR image, and the HDR environment map can have a higher dynamic range than that of the LDR environment map. Therefore, a light source suitable for an input image can be extracted in a form of the HDR environment map. 심층 학습(Deep Learning)에 기반하여 LDR(Low Dynamic Range) 영상으로부터 HDR(High Dynamic Range) 환경 맵(Environment Map)을 제공하는 방법이 개시된다. 개시된 방법은, LDR 영상을 제1 DNN(Deep Neural Network) 네트워크로 입력하여 LDR 환경 맵을 출력하는 단계, 및 상기 LDR 환경 맵을 제2 DNN 네트워크로 입력하여 HDR 환경 맵을 출력하는 단계를 포함할 수 있다. 상기 LDR 환경 맵은 상기 LDR 영상에서의 광원의 위치와 세기를 나타내는 정보 및 상기 LDR 영상의 색감에 관한 정보를 포함하고, 상기 HDR 환경 맵은 상기 LDR 환경 맵에 비해 높은 동적 범위(Dynamic Range)를 가질 수 있다.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20230078146A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20230078146A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20230078146A3</originalsourceid><addsrcrecordid>eNqNjMEKgkAURd20iOofHrQOTKPaWhpGCiHt5dG8MSPfG2Ymvz-NPqDF5S7OuXcaPIu0gnxISf4hCpAVJMagRf92oMXC1UrfqpabgX3NjPvWCnfEHko0oK10Ixufzh02BAd0pEAYUiIDBaHlYT8PJhpfjha_ngXLU3Y75isyUpMzeCcmX1-qKIziMNzt15ttEv9nfQCTBj5_</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>LDR HDR Method and Apparatus for Providing an HDR Environment Map from an LDR Image Based on Deep Learning</title><source>esp@cenet</source><creator>LEE JI WON ; YOO JUNG EUN ; SEO KWANG GYOON ; NOH JUN YONG ; LEE HA NUI</creator><creatorcontrib>LEE JI WON ; YOO JUNG EUN ; SEO KWANG GYOON ; NOH JUN YONG ; LEE HA NUI</creatorcontrib><description>Disclosed is a method for providing a high dynamic range (HDR) environment map from a low dynamic range (LDR) image based on deep learning. The method comprises the steps of: inputting an LDR image into a first deep neural network (DNN), and outputting an LDR environment map; and inputting the LDR environment map into a second DNN to output an HDR environment map. The LDR environment map includes information indicating the location and intensity of a light source in the LDR image and information on a color of the LDR image, and the HDR environment map can have a higher dynamic range than that of the LDR environment map. Therefore, a light source suitable for an input image can be extracted in a form of the HDR environment map. 심층 학습(Deep Learning)에 기반하여 LDR(Low Dynamic Range) 영상으로부터 HDR(High Dynamic Range) 환경 맵(Environment Map)을 제공하는 방법이 개시된다. 개시된 방법은, LDR 영상을 제1 DNN(Deep Neural Network) 네트워크로 입력하여 LDR 환경 맵을 출력하는 단계, 및 상기 LDR 환경 맵을 제2 DNN 네트워크로 입력하여 HDR 환경 맵을 출력하는 단계를 포함할 수 있다. 상기 LDR 환경 맵은 상기 LDR 영상에서의 광원의 위치와 세기를 나타내는 정보 및 상기 LDR 영상의 색감에 관한 정보를 포함하고, 상기 HDR 환경 맵은 상기 LDR 환경 맵에 비해 높은 동적 범위(Dynamic Range)를 가질 수 있다.</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>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&amp;date=20230602&amp;DB=EPODOC&amp;CC=KR&amp;NR=20230078146A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25569,76552</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230602&amp;DB=EPODOC&amp;CC=KR&amp;NR=20230078146A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LEE JI WON</creatorcontrib><creatorcontrib>YOO JUNG EUN</creatorcontrib><creatorcontrib>SEO KWANG GYOON</creatorcontrib><creatorcontrib>NOH JUN YONG</creatorcontrib><creatorcontrib>LEE HA NUI</creatorcontrib><title>LDR HDR Method and Apparatus for Providing an HDR Environment Map from an LDR Image Based on Deep Learning</title><description>Disclosed is a method for providing a high dynamic range (HDR) environment map from a low dynamic range (LDR) image based on deep learning. The method comprises the steps of: inputting an LDR image into a first deep neural network (DNN), and outputting an LDR environment map; and inputting the LDR environment map into a second DNN to output an HDR environment map. The LDR environment map includes information indicating the location and intensity of a light source in the LDR image and information on a color of the LDR image, and the HDR environment map can have a higher dynamic range than that of the LDR environment map. Therefore, a light source suitable for an input image can be extracted in a form of the HDR environment map. 심층 학습(Deep Learning)에 기반하여 LDR(Low Dynamic Range) 영상으로부터 HDR(High Dynamic Range) 환경 맵(Environment Map)을 제공하는 방법이 개시된다. 개시된 방법은, LDR 영상을 제1 DNN(Deep Neural Network) 네트워크로 입력하여 LDR 환경 맵을 출력하는 단계, 및 상기 LDR 환경 맵을 제2 DNN 네트워크로 입력하여 HDR 환경 맵을 출력하는 단계를 포함할 수 있다. 상기 LDR 환경 맵은 상기 LDR 영상에서의 광원의 위치와 세기를 나타내는 정보 및 상기 LDR 영상의 색감에 관한 정보를 포함하고, 상기 HDR 환경 맵은 상기 LDR 환경 맵에 비해 높은 동적 범위(Dynamic Range)를 가질 수 있다.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjMEKgkAURd20iOofHrQOTKPaWhpGCiHt5dG8MSPfG2Ymvz-NPqDF5S7OuXcaPIu0gnxISf4hCpAVJMagRf92oMXC1UrfqpabgX3NjPvWCnfEHko0oK10Ixufzh02BAd0pEAYUiIDBaHlYT8PJhpfjha_ngXLU3Y75isyUpMzeCcmX1-qKIziMNzt15ttEv9nfQCTBj5_</recordid><startdate>20230602</startdate><enddate>20230602</enddate><creator>LEE JI WON</creator><creator>YOO JUNG EUN</creator><creator>SEO KWANG GYOON</creator><creator>NOH JUN YONG</creator><creator>LEE HA NUI</creator><scope>EVB</scope></search><sort><creationdate>20230602</creationdate><title>LDR HDR Method and Apparatus for Providing an HDR Environment Map from an LDR Image Based on Deep Learning</title><author>LEE JI WON ; YOO JUNG EUN ; SEO KWANG GYOON ; NOH JUN YONG ; LEE HA NUI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20230078146A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2023</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>LEE JI WON</creatorcontrib><creatorcontrib>YOO JUNG EUN</creatorcontrib><creatorcontrib>SEO KWANG GYOON</creatorcontrib><creatorcontrib>NOH JUN YONG</creatorcontrib><creatorcontrib>LEE HA NUI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LEE JI WON</au><au>YOO JUNG EUN</au><au>SEO KWANG GYOON</au><au>NOH JUN YONG</au><au>LEE HA NUI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>LDR HDR Method and Apparatus for Providing an HDR Environment Map from an LDR Image Based on Deep Learning</title><date>2023-06-02</date><risdate>2023</risdate><abstract>Disclosed is a method for providing a high dynamic range (HDR) environment map from a low dynamic range (LDR) image based on deep learning. The method comprises the steps of: inputting an LDR image into a first deep neural network (DNN), and outputting an LDR environment map; and inputting the LDR environment map into a second DNN to output an HDR environment map. The LDR environment map includes information indicating the location and intensity of a light source in the LDR image and information on a color of the LDR image, and the HDR environment map can have a higher dynamic range than that of the LDR environment map. Therefore, a light source suitable for an input image can be extracted in a form of the HDR environment map. 심층 학습(Deep Learning)에 기반하여 LDR(Low Dynamic Range) 영상으로부터 HDR(High Dynamic Range) 환경 맵(Environment Map)을 제공하는 방법이 개시된다. 개시된 방법은, LDR 영상을 제1 DNN(Deep Neural Network) 네트워크로 입력하여 LDR 환경 맵을 출력하는 단계, 및 상기 LDR 환경 맵을 제2 DNN 네트워크로 입력하여 HDR 환경 맵을 출력하는 단계를 포함할 수 있다. 상기 LDR 환경 맵은 상기 LDR 영상에서의 광원의 위치와 세기를 나타내는 정보 및 상기 LDR 영상의 색감에 관한 정보를 포함하고, 상기 HDR 환경 맵은 상기 LDR 환경 맵에 비해 높은 동적 범위(Dynamic Range)를 가질 수 있다.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; kor
recordid cdi_epo_espacenet_KR20230078146A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title LDR HDR Method and Apparatus for Providing an HDR Environment Map from an LDR Image Based on Deep Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-13T05%3A22%3A23IST&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=LEE%20JI%20WON&rft.date=2023-06-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20230078146A%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