Generative latent textured proxies for object category modeling

Generative latent textured proxies for object category modeling

Systems and methods are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Goldman, Daniel, Pandey, Rohit Kumar, Martin Brualla, Ricardo, Brown, Matthew, Bouaziz, Sofien
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
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 Goldman, Daniel
Pandey, Rohit Kumar
Martin Brualla, Ricardo
Brown, Matthew
Bouaziz, Sofien
description Systems and methods are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances representing the object, providing the plurality of neural textures to a neural renderer, receiving, from the neural renderer and based on the plurality of neural textures, a color image and an alpha mask representing an opacity of at least a portion of the object, and generating a composite image based on the pose, the color image, and the alpha mask.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11710287B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11710287B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11710287B23</originalsourceid><addsrcrecordid>eNrjZLB3T81LLUosySxLVchJLEnNK1EoSa0oKS1KTVEoKMqvyEwtVkjLL1LIT8pKTS5RSAYqSc8vqlTIzU9JzcnMS-dhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJQPNL4kODDQ3NDQ2MLMydjIyJUQMA3y0xrA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Generative latent textured proxies for object category modeling</title><source>esp@cenet</source><creator>Goldman, Daniel ; Pandey, Rohit Kumar ; Martin Brualla, Ricardo ; Brown, Matthew ; Bouaziz, Sofien</creator><creatorcontrib>Goldman, Daniel ; Pandey, Rohit Kumar ; Martin Brualla, Ricardo ; Brown, Matthew ; Bouaziz, Sofien</creatorcontrib><description>Systems and methods are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances representing the object, providing the plurality of neural textures to a neural renderer, receiving, from the neural renderer and based on the plurality of neural textures, a color image and an alpha mask representing an opacity of at least a portion of the object, and generating a composite image based on the pose, the color image, and the alpha mask.</description><language>eng</language><subject>CALCULATING ; 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=20230725&amp;DB=EPODOC&amp;CC=US&amp;NR=11710287B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230725&amp;DB=EPODOC&amp;CC=US&amp;NR=11710287B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Goldman, Daniel</creatorcontrib><creatorcontrib>Pandey, Rohit Kumar</creatorcontrib><creatorcontrib>Martin Brualla, Ricardo</creatorcontrib><creatorcontrib>Brown, Matthew</creatorcontrib><creatorcontrib>Bouaziz, Sofien</creatorcontrib><title>Generative latent textured proxies for object category modeling</title><description>Systems and methods are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances representing the object, providing the plurality of neural textures to a neural renderer, receiving, from the neural renderer and based on the plurality of neural textures, a color image and an alpha mask representing an opacity of at least a portion of the object, and generating a composite image based on the pose, the color image, and the alpha mask.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLB3T81LLUosySxLVchJLEnNK1EoSa0oKS1KTVEoKMqvyEwtVkjLL1LIT8pKTS5RSAYqSc8vqlTIzU9JzcnMS-dhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJQPNL4kODDQ3NDQ2MLMydjIyJUQMA3y0xrA</recordid><startdate>20230725</startdate><enddate>20230725</enddate><creator>Goldman, Daniel</creator><creator>Pandey, Rohit Kumar</creator><creator>Martin Brualla, Ricardo</creator><creator>Brown, Matthew</creator><creator>Bouaziz, Sofien</creator><scope>EVB</scope></search><sort><creationdate>20230725</creationdate><title>Generative latent textured proxies for object category modeling</title><author>Goldman, Daniel ; Pandey, Rohit Kumar ; Martin Brualla, Ricardo ; Brown, Matthew ; Bouaziz, Sofien</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11710287B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</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>Goldman, Daniel</creatorcontrib><creatorcontrib>Pandey, Rohit Kumar</creatorcontrib><creatorcontrib>Martin Brualla, Ricardo</creatorcontrib><creatorcontrib>Brown, Matthew</creatorcontrib><creatorcontrib>Bouaziz, Sofien</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Goldman, Daniel</au><au>Pandey, Rohit Kumar</au><au>Martin Brualla, Ricardo</au><au>Brown, Matthew</au><au>Bouaziz, Sofien</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Generative latent textured proxies for object category modeling</title><date>2023-07-25</date><risdate>2023</risdate><abstract>Systems and methods are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances representing the object, providing the plurality of neural textures to a neural renderer, receiving, from the neural renderer and based on the plurality of neural textures, a color image and an alpha mask representing an opacity of at least a portion of the object, and generating a composite image based on the pose, the color image, and the alpha mask.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11710287B2
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Generative latent textured proxies for object category modeling
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T12%3A54%3A33IST&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=Goldman,%20Daniel&rft.date=2023-07-25&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11710287B2%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