METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS
Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes: (i) a group of one-light-at-a-time (OLAT) images that have each been capt...
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 | KOWDLE ADARSH PRAKASH MURTHY HARVEY GEOFFREY DOUGLAS DENNY PETER JOSEPH IZADI SHAHRAM DEBEVEC PAUL VALENTIN JULIEN PASCAL CHRISTOPHE RHEMANN CHRISTOPH BOUAZIZ SOFIEN FANELLO SEAN RYAN FRANCESCO DOURGARIAN JASON ANGELO TAYLOR JONATHAN FYFFE GRAHAM YU XUEMING BUSCH JESSICA LYNN PANDEY ROHIT KUMAR HANE CHRISTIAN MEKA ABHIMITRA WHALEN MATTHEW LINCOLN PETER CHRISTOPHER TAGLIASACCHI ANDREA |
| description | Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes: (i) a group of one-light-at-a-time (OLAT) images that have each been captured when one light of a plurality of lights arranged on a lighting structure has been activated, (ii) a group of spherical color gradient images that have each been captured when the plurality of lights arranged on the lighting structure have been activated to each emit a particular color, and (iii) a lighting direction, wherein each image in the group of OLAT images and each of the spherical color gradient images are an image of a subject, and wherein the lighting direction indicates a relative orientation of a light to the subject; training a convolutional neural network using the group of training samples, wherein training the convolutional neural network comprises: for each training iteration in a series of tr |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113661496A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113661496A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113661496A3</originalsourceid><addsrcrecordid>eNqNyr0KwjAUhuEuDqLew3HXIVQCjiE5-YEkLTnp0KkUiZNood4_RvACnL73g2fbjAGz7RSdgEbKGGqIqCCgcgJ0lyChd8ZmFw24IAwSDPQ9fapEZlSgEPvKtEeZRZQI2qFXtG829_mxlsNvd81RY5b2XJbXVNZlvpVneU8yMtZyzi5XLtp_zAfnGjEW</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS</title><source>esp@cenet</source><creator>KOWDLE ADARSH PRAKASH MURTHY ; HARVEY GEOFFREY DOUGLAS ; DENNY PETER JOSEPH ; IZADI SHAHRAM ; DEBEVEC PAUL ; VALENTIN JULIEN PASCAL CHRISTOPHE ; RHEMANN CHRISTOPH ; BOUAZIZ SOFIEN ; FANELLO SEAN RYAN FRANCESCO ; DOURGARIAN JASON ANGELO ; TAYLOR JONATHAN ; FYFFE GRAHAM ; YU XUEMING ; BUSCH JESSICA LYNN ; PANDEY ROHIT KUMAR ; HANE CHRISTIAN ; MEKA ABHIMITRA ; WHALEN MATTHEW ; LINCOLN PETER CHRISTOPHER ; TAGLIASACCHI ANDREA</creator><creatorcontrib>KOWDLE ADARSH PRAKASH MURTHY ; HARVEY GEOFFREY DOUGLAS ; DENNY PETER JOSEPH ; IZADI SHAHRAM ; DEBEVEC PAUL ; VALENTIN JULIEN PASCAL CHRISTOPHE ; RHEMANN CHRISTOPH ; BOUAZIZ SOFIEN ; FANELLO SEAN RYAN FRANCESCO ; DOURGARIAN JASON ANGELO ; TAYLOR JONATHAN ; FYFFE GRAHAM ; YU XUEMING ; BUSCH JESSICA LYNN ; PANDEY ROHIT KUMAR ; HANE CHRISTIAN ; MEKA ABHIMITRA ; WHALEN MATTHEW ; LINCOLN PETER CHRISTOPHER ; TAGLIASACCHI ANDREA</creatorcontrib><description>Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes: (i) a group of one-light-at-a-time (OLAT) images that have each been captured when one light of a plurality of lights arranged on a lighting structure has been activated, (ii) a group of spherical color gradient images that have each been captured when the plurality of lights arranged on the lighting structure have been activated to each emit a particular color, and (iii) a lighting direction, wherein each image in the group of OLAT images and each of the spherical color gradient images are an image of a subject, and wherein the lighting direction indicates a relative orientation of a light to the subject; training a convolutional neural network using the group of training samples, wherein training the convolutional neural network comprises: for each training iteration in a series of tr</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2021</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=20211116&DB=EPODOC&CC=CN&NR=113661496A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211116&DB=EPODOC&CC=CN&NR=113661496A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KOWDLE ADARSH PRAKASH MURTHY</creatorcontrib><creatorcontrib>HARVEY GEOFFREY DOUGLAS</creatorcontrib><creatorcontrib>DENNY PETER JOSEPH</creatorcontrib><creatorcontrib>IZADI SHAHRAM</creatorcontrib><creatorcontrib>DEBEVEC PAUL</creatorcontrib><creatorcontrib>VALENTIN JULIEN PASCAL CHRISTOPHE</creatorcontrib><creatorcontrib>RHEMANN CHRISTOPH</creatorcontrib><creatorcontrib>BOUAZIZ SOFIEN</creatorcontrib><creatorcontrib>FANELLO SEAN RYAN FRANCESCO</creatorcontrib><creatorcontrib>DOURGARIAN JASON ANGELO</creatorcontrib><creatorcontrib>TAYLOR JONATHAN</creatorcontrib><creatorcontrib>FYFFE GRAHAM</creatorcontrib><creatorcontrib>YU XUEMING</creatorcontrib><creatorcontrib>BUSCH JESSICA LYNN</creatorcontrib><creatorcontrib>PANDEY ROHIT KUMAR</creatorcontrib><creatorcontrib>HANE CHRISTIAN</creatorcontrib><creatorcontrib>MEKA ABHIMITRA</creatorcontrib><creatorcontrib>WHALEN MATTHEW</creatorcontrib><creatorcontrib>LINCOLN PETER CHRISTOPHER</creatorcontrib><creatorcontrib>TAGLIASACCHI ANDREA</creatorcontrib><title>METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS</title><description>Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes: (i) a group of one-light-at-a-time (OLAT) images that have each been captured when one light of a plurality of lights arranged on a lighting structure has been activated, (ii) a group of spherical color gradient images that have each been captured when the plurality of lights arranged on the lighting structure have been activated to each emit a particular color, and (iii) a lighting direction, wherein each image in the group of OLAT images and each of the spherical color gradient images are an image of a subject, and wherein the lighting direction indicates a relative orientation of a light to the subject; training a convolutional neural network using the group of training samples, wherein training the convolutional neural network comprises: for each training iteration in a series of tr</description><subject>CALCULATING</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyr0KwjAUhuEuDqLew3HXIVQCjiE5-YEkLTnp0KkUiZNood4_RvACnL73g2fbjAGz7RSdgEbKGGqIqCCgcgJ0lyChd8ZmFw24IAwSDPQ9fapEZlSgEPvKtEeZRZQI2qFXtG829_mxlsNvd81RY5b2XJbXVNZlvpVneU8yMtZyzi5XLtp_zAfnGjEW</recordid><startdate>20211116</startdate><enddate>20211116</enddate><creator>KOWDLE ADARSH PRAKASH MURTHY</creator><creator>HARVEY GEOFFREY DOUGLAS</creator><creator>DENNY PETER JOSEPH</creator><creator>IZADI SHAHRAM</creator><creator>DEBEVEC PAUL</creator><creator>VALENTIN JULIEN PASCAL CHRISTOPHE</creator><creator>RHEMANN CHRISTOPH</creator><creator>BOUAZIZ SOFIEN</creator><creator>FANELLO SEAN RYAN FRANCESCO</creator><creator>DOURGARIAN JASON ANGELO</creator><creator>TAYLOR JONATHAN</creator><creator>FYFFE GRAHAM</creator><creator>YU XUEMING</creator><creator>BUSCH JESSICA LYNN</creator><creator>PANDEY ROHIT KUMAR</creator><creator>HANE CHRISTIAN</creator><creator>MEKA ABHIMITRA</creator><creator>WHALEN MATTHEW</creator><creator>LINCOLN PETER CHRISTOPHER</creator><creator>TAGLIASACCHI ANDREA</creator><scope>EVB</scope></search><sort><creationdate>20211116</creationdate><title>METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS</title><author>KOWDLE ADARSH PRAKASH MURTHY ; HARVEY GEOFFREY DOUGLAS ; DENNY PETER JOSEPH ; IZADI SHAHRAM ; DEBEVEC PAUL ; VALENTIN JULIEN PASCAL CHRISTOPHE ; RHEMANN CHRISTOPH ; BOUAZIZ SOFIEN ; FANELLO SEAN RYAN FRANCESCO ; DOURGARIAN JASON ANGELO ; TAYLOR JONATHAN ; FYFFE GRAHAM ; YU XUEMING ; BUSCH JESSICA LYNN ; PANDEY ROHIT KUMAR ; HANE CHRISTIAN ; MEKA ABHIMITRA ; WHALEN MATTHEW ; LINCOLN PETER CHRISTOPHER ; TAGLIASACCHI ANDREA</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113661496A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KOWDLE ADARSH PRAKASH MURTHY</creatorcontrib><creatorcontrib>HARVEY GEOFFREY DOUGLAS</creatorcontrib><creatorcontrib>DENNY PETER JOSEPH</creatorcontrib><creatorcontrib>IZADI SHAHRAM</creatorcontrib><creatorcontrib>DEBEVEC PAUL</creatorcontrib><creatorcontrib>VALENTIN JULIEN PASCAL CHRISTOPHE</creatorcontrib><creatorcontrib>RHEMANN CHRISTOPH</creatorcontrib><creatorcontrib>BOUAZIZ SOFIEN</creatorcontrib><creatorcontrib>FANELLO SEAN RYAN FRANCESCO</creatorcontrib><creatorcontrib>DOURGARIAN JASON ANGELO</creatorcontrib><creatorcontrib>TAYLOR JONATHAN</creatorcontrib><creatorcontrib>FYFFE GRAHAM</creatorcontrib><creatorcontrib>YU XUEMING</creatorcontrib><creatorcontrib>BUSCH JESSICA LYNN</creatorcontrib><creatorcontrib>PANDEY ROHIT KUMAR</creatorcontrib><creatorcontrib>HANE CHRISTIAN</creatorcontrib><creatorcontrib>MEKA ABHIMITRA</creatorcontrib><creatorcontrib>WHALEN MATTHEW</creatorcontrib><creatorcontrib>LINCOLN PETER CHRISTOPHER</creatorcontrib><creatorcontrib>TAGLIASACCHI ANDREA</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KOWDLE ADARSH PRAKASH MURTHY</au><au>HARVEY GEOFFREY DOUGLAS</au><au>DENNY PETER JOSEPH</au><au>IZADI SHAHRAM</au><au>DEBEVEC PAUL</au><au>VALENTIN JULIEN PASCAL CHRISTOPHE</au><au>RHEMANN CHRISTOPH</au><au>BOUAZIZ SOFIEN</au><au>FANELLO SEAN RYAN FRANCESCO</au><au>DOURGARIAN JASON ANGELO</au><au>TAYLOR JONATHAN</au><au>FYFFE GRAHAM</au><au>YU XUEMING</au><au>BUSCH JESSICA LYNN</au><au>PANDEY ROHIT KUMAR</au><au>HANE CHRISTIAN</au><au>MEKA ABHIMITRA</au><au>WHALEN MATTHEW</au><au>LINCOLN PETER CHRISTOPHER</au><au>TAGLIASACCHI ANDREA</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS</title><date>2021-11-16</date><risdate>2021</risdate><abstract>Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes: (i) a group of one-light-at-a-time (OLAT) images that have each been captured when one light of a plurality of lights arranged on a lighting structure has been activated, (ii) a group of spherical color gradient images that have each been captured when the plurality of lights arranged on the lighting structure have been activated to each emit a particular color, and (iii) a lighting direction, wherein each image in the group of OLAT images and each of the spherical color gradient images are an image of a subject, and wherein the lighting direction indicates a relative orientation of a light to the subject; training a convolutional neural network using the group of training samples, wherein training the convolutional neural network comprises: for each training iteration in a series of tr</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN113661496A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T02%3A50%3A05IST&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=KOWDLE%20ADARSH%20PRAKASH%20MURTHY&rft.date=2021-11-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113661496A%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 |