MULTIRESOLUTION TRUNCATED NEURAL RADIANCE FIELDS

A system and method for receiving colour images, depth images and viewpoint information; dividing 3D space occupied by real-world environment into 3D grid(s) of voxels; create 3D data structure(s) comprising nodes, each node representing corresponding voxel; dividing colour image and depth image int...

Full description

Saved in:
Bibliographic Details
Main Authors Strandborg, Mikko, Roimela, Kimmo
Format Patent
LanguageEnglish
Published 22.08.2024
Subjects
Online AccessGet full text

Cover

Loading…
Abstract A system and method for receiving colour images, depth images and viewpoint information; dividing 3D space occupied by real-world environment into 3D grid(s) of voxels; create 3D data structure(s) comprising nodes, each node representing corresponding voxel; dividing colour image and depth image into colour tiles and depth tiles, respectively; mapping colour tile to voxel(s) whose colour information is captured in colour tile; storing, in node representing voxel(s), viewpoint information indicative of viewpoint from which colour and depth images are captured, along with any of: colour tile that captures colour information of voxel(s) and corresponding depth tile that captured depth information, or reference information indicative of unique identification of colour tile and corresponding depth tile; and utilising 3D data structure(s) for training neural network(s), wherein input of neural network(s) comprises 3D position of point and output of neural network(s) comprises colour and opacity of point.
AbstractList A system and method for receiving colour images, depth images and viewpoint information; dividing 3D space occupied by real-world environment into 3D grid(s) of voxels; create 3D data structure(s) comprising nodes, each node representing corresponding voxel; dividing colour image and depth image into colour tiles and depth tiles, respectively; mapping colour tile to voxel(s) whose colour information is captured in colour tile; storing, in node representing voxel(s), viewpoint information indicative of viewpoint from which colour and depth images are captured, along with any of: colour tile that captures colour information of voxel(s) and corresponding depth tile that captured depth information, or reference information indicative of unique identification of colour tile and corresponding depth tile; and utilising 3D data structure(s) for training neural network(s), wherein input of neural network(s) comprises 3D position of point and output of neural network(s) comprises colour and opacity of point.
Author Roimela, Kimmo
Strandborg, Mikko
Author_xml – fullname: Strandborg, Mikko
– fullname: Roimela, Kimmo
BookMark eNrjYmDJy89L5WQw8A31CfEMcg329wkN8fT3UwgJCvVzdgxxdVHwcw0NcvRRCHJ08XT0c3ZVcPN09XEJ5mFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgZGJkYWRgamho6GxsSpAgDy8Ck7
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US2024282051A1
GroupedDBID EVB
ID FETCH-epo_espacenet_US2024282051A13
IEDL.DBID EVB
IngestDate Fri Sep 20 10:17:46 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US2024282051A13
Notes Application Number: US202318111340
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240822&DB=EPODOC&CC=US&NR=2024282051A1
ParticipantIDs epo_espacenet_US2024282051A1
PublicationCentury 2000
PublicationDate 20240822
PublicationDateYYYYMMDD 2024-08-22
PublicationDate_xml – month: 08
  year: 2024
  text: 20240822
  day: 22
PublicationDecade 2020
PublicationYear 2024
RelatedCompanies Varjo Technologies Oy
RelatedCompanies_xml – name: Varjo Technologies Oy
Score 3.5499878
Snippet A system and method for receiving colour images, depth images and viewpoint information; dividing 3D space occupied by real-world environment into 3D grid(s)...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Title MULTIRESOLUTION TRUNCATED NEURAL RADIANCE FIELDS
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240822&DB=EPODOC&locale=&CC=US&NR=2024282051A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Za8MwDBalO9-2bGNHNwIbeQtLnYPlIYw0B83IUZJ49K00R2Ew0rJk7O9PNunWpz5aBiMLyZZk6TPAk6FhEICaISvqSpU1ZopmYYzlcfmioDO3NHSddSNHsTGl2ttcnw_gc9sLw3FCfzg4IlpUifbe8fN685_EcnltZftcfCBp_ernliv10THD6yJEcieWN0vcxJEcx6KZFKd8DqMLVEEbY6UD5kgzpH3vfcL6Uja7l4p_BoczXK_pzmFQNwKcONu_1wQ4jvonbwGOeI1m2SKxt8P2ApSIhnmAwktCynJMYp7S2LHxFBJjj6Z2KKa2G7B_Z0Q_8EI3u4RH38udqYxMLP72vKDZLsfqFQybdVNfg8ghuMxKIVVVaKTSTFKhD1ab6nJVFvW4vIHRvpVu90_fwSkbsqQpISMYdl_f9T3eul3xwIX1C6vZfwM
link.rule.ids 230,309,786,891,25594,76906
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1ZS8NAEB5KPeqbRsWjakDJWzDdHJqHImkOGs1Rkqz0rTRHQZC0mIh_39ml1T71dQaG3WVmdmZ25luAB0PDJAA1Q1bUhSprzBTN3BjIg-JZwWBubug6m0YOI2NMtdepPu3A52YWhuOE_nBwRLSoAu295f569V_EcnhvZfOYfyBp-eJlQ0daZ8cMr4sQyRkN3UnsxLZk20OaSlHCeZhdoApamCvtPTF8XhY8vY_YXMpq-1LxjmF_gvLq9gQ6VS1Az978vSbAYbh-8hbggPdoFg0S13bYnIIS0iDz8fDigLIak5glNLIt9EJi5NLECsTEcnz274zo-W7gpGdw77mZPZZxEbO_Pc9our1i9Ry69bKuLkDkEFxmqZCyzDVSaiYpMQarTHW-KPJqUFxCf5ekq93sO-iNszCYBX70dg1HjMUKqIT0odt-fVc3eAO3-S0_uF_Ew4Hw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=MULTIRESOLUTION+TRUNCATED+NEURAL+RADIANCE+FIELDS&rft.inventor=Strandborg%2C+Mikko&rft.inventor=Roimela%2C+Kimmo&rft.date=2024-08-22&rft.externalDBID=A1&rft.externalDocID=US2024282051A1