Relighting system for single images
In various embodiments, a computer-implemented method of training a neural network for relighting an image is described. A first training set that includes source images and a target illumination embedding is generated, the source images having respective illuminated subjects. A second training set...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| 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 | Neofytou, Alexandros Sommerlade, Eric Chris Wolfgang Liu, Yang Sengupta, Sunando |
| description | In various embodiments, a computer-implemented method of training a neural network for relighting an image is described. A first training set that includes source images and a target illumination embedding is generated, the source images having respective illuminated subjects. A second training set that includes augmented images and the target illumination embedding is generated, where the augmented images corresponding to the source images. A first autoencoder is trained using the first training set to generate a first output set that includes estimated source illumination embeddings and first reconstructed images that correspond to the source images, the reconstructed images having respective subjects that are i) from the corresponding source image, and ii) illuminated based on the target illumination embedding. A second autoencoder is trained using the second training set to generate a second output set that includes estimated augmented illumination embeddings and second reconstructed images that correspond to the augmented images. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11915398B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11915398B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11915398B23</originalsourceid><addsrcrecordid>eNrjZFAOSs3JTM8oycxLVyiuLC5JzVVIyy9SKAbyc1IVMnMT01OLeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJfGiwoaGloamxpYWTkTExagDyoia5</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Relighting system for single images</title><source>esp@cenet</source><creator>Neofytou, Alexandros ; Sommerlade, Eric Chris Wolfgang ; Liu, Yang ; Sengupta, Sunando</creator><creatorcontrib>Neofytou, Alexandros ; Sommerlade, Eric Chris Wolfgang ; Liu, Yang ; Sengupta, Sunando</creatorcontrib><description>In various embodiments, a computer-implemented method of training a neural network for relighting an image is described. A first training set that includes source images and a target illumination embedding is generated, the source images having respective illuminated subjects. A second training set that includes augmented images and the target illumination embedding is generated, where the augmented images corresponding to the source images. A first autoencoder is trained using the first training set to generate a first output set that includes estimated source illumination embeddings and first reconstructed images that correspond to the source images, the reconstructed images having respective subjects that are i) from the corresponding source image, and ii) illuminated based on the target illumination embedding. A second autoencoder is trained using the second training set to generate a second output set that includes estimated augmented illumination embeddings and second reconstructed images that correspond to the augmented images.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2024</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=20240227&DB=EPODOC&CC=US&NR=11915398B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25569,76552</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240227&DB=EPODOC&CC=US&NR=11915398B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Neofytou, Alexandros</creatorcontrib><creatorcontrib>Sommerlade, Eric Chris Wolfgang</creatorcontrib><creatorcontrib>Liu, Yang</creatorcontrib><creatorcontrib>Sengupta, Sunando</creatorcontrib><title>Relighting system for single images</title><description>In various embodiments, a computer-implemented method of training a neural network for relighting an image is described. A first training set that includes source images and a target illumination embedding is generated, the source images having respective illuminated subjects. A second training set that includes augmented images and the target illumination embedding is generated, where the augmented images corresponding to the source images. A first autoencoder is trained using the first training set to generate a first output set that includes estimated source illumination embeddings and first reconstructed images that correspond to the source images, the reconstructed images having respective subjects that are i) from the corresponding source image, and ii) illuminated based on the target illumination embedding. A second autoencoder is trained using the second training set to generate a second output set that includes estimated augmented illumination embeddings and second reconstructed images that correspond to the augmented images.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFAOSs3JTM8oycxLVyiuLC5JzVVIyy9SKAbyc1IVMnMT01OLeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJfGiwoaGloamxpYWTkTExagDyoia5</recordid><startdate>20240227</startdate><enddate>20240227</enddate><creator>Neofytou, Alexandros</creator><creator>Sommerlade, Eric Chris Wolfgang</creator><creator>Liu, Yang</creator><creator>Sengupta, Sunando</creator><scope>EVB</scope></search><sort><creationdate>20240227</creationdate><title>Relighting system for single images</title><author>Neofytou, Alexandros ; Sommerlade, Eric Chris Wolfgang ; Liu, Yang ; Sengupta, Sunando</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11915398B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Neofytou, Alexandros</creatorcontrib><creatorcontrib>Sommerlade, Eric Chris Wolfgang</creatorcontrib><creatorcontrib>Liu, Yang</creatorcontrib><creatorcontrib>Sengupta, Sunando</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Neofytou, Alexandros</au><au>Sommerlade, Eric Chris Wolfgang</au><au>Liu, Yang</au><au>Sengupta, Sunando</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Relighting system for single images</title><date>2024-02-27</date><risdate>2024</risdate><abstract>In various embodiments, a computer-implemented method of training a neural network for relighting an image is described. A first training set that includes source images and a target illumination embedding is generated, the source images having respective illuminated subjects. A second training set that includes augmented images and the target illumination embedding is generated, where the augmented images corresponding to the source images. A first autoencoder is trained using the first training set to generate a first output set that includes estimated source illumination embeddings and first reconstructed images that correspond to the source images, the reconstructed images having respective subjects that are i) from the corresponding source image, and ii) illuminated based on the target illumination embedding. A second autoencoder is trained using the second training set to generate a second output set that includes estimated augmented illumination embeddings and second reconstructed images that correspond to the augmented images.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US11915398B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Relighting system for single images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-11T15%3A33%3A40IST&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=Neofytou,%20Alexandros&rft.date=2024-02-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11915398B2%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 |