Please use this identifier to cite or link to this item: https://dspace.crs4.it/jspui/handle/1138/33
DC FieldValueLanguage
dc.contributor.authorPintore, Giovannien_US
dc.contributor.authorAlmansa Aránega, Eva Maríaen_US
dc.contributor.authorAgus, Marcoen_US
dc.contributor.authorGobbetti, Enricoen_US
dc.date.accessioned2021-09-21T15:27:20Z-
dc.date.available2021-09-21T15:27:20Z-
dc.date.issued2021-12-
dc.identifier.urihttps://dspace.crs4.it/jspui/handle/1138/33-
dc.description.abstractRecovering the 3D shape of the bounding permanent surfaces of a room from a single image is a key component of indoor reconstruction pipelines. In this article, we introduce a novel deep learning technique capable to produce, at interactive rates, a tessellated bounding 3D surface from a single 360-degree image. Differently from prior solutions, we fully address the problem in 3D, significantly expanding the reconstruction space of prior solutions. A graph convolutional network directly infers the room structure as a 3D mesh by progressively deforming a graph-encoded tessellated sphere mapped to the spherical panorama, leveraging perceptual features extracted from the input image. Important 3D properties of indoor environments are exploited in our design. In particular, gravity-aligned features are actively incorporated in the graph in a projection layer that exploits the recent concept of multi head self-attention, and specialized losses guide towards plausible solutions even in presence of massive clutter and occlusions. Extensive experiments demonstrate that our approach outperforms current state of the art methods in terms of accuracy and capability to reconstruct more complex environments.en_US
dc.language.isoenen_US
dc.publisherACMen_US
dc.relationAdvanced Visual and Geometric Computing for 3D Capture, Display, and Fabricationen_US
dc.relationVIGECLABen_US
dc.relation.ispartofACM Transactions on Graphicsen_US
dc.subjectindoor 3D layout, panoramic images, data-driven reconstruction, structured indoor reconstructionen_US
dc.titleDeep3DLayout: 3D Reconstruction of an Indoor Layout from a Spherical Panoramic Imageen_US
dc.typejournal articleen_US
dc.relation.conferenceProc. SIGGRAPH Asiaen_US
dc.identifier.doi10.1145/3478513.3480480-
dc.contributor.affiliationCRS4en_US
dc.contributor.affiliationCRS4en_US
dc.contributor.affiliationHBKUen_US
dc.contributor.affiliationCRS4en_US
dc.description.volume40en_US
dc.description.issue6en_US
dc.description.startpage250:1en_US
dc.description.endpage250:12en_US
dc.relation.grantno813170en_US
dc.relation.grantnoPOR FESR 2014-2020en_US
item.languageiso639-1en-
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.grantfulltextopen-
item.cerifentitytypePublications-
item.fulltextWith Fulltext-
item.openairetypejournal article-
crisitem.project.funderEC-
crisitem.project.projectURLwww.evocation.eu-
crisitem.project.fundingProgramH2020-
crisitem.project.openAireinfo:eu-repo/grantAgreement/EC/H2020/813170-
crisitem.author.deptCRS4-
crisitem.author.deptCRS4-
crisitem.author.deptCRS4-
crisitem.author.orcid0000-0002-7288-0989-
Appears in Collections:CRS4 publications
Files in This Item:
File Description SizeFormat
sigasia2021-deep3dlayout.pdfGreen OA Version15,92 MBAdobe PDFView/Open
Show simple item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.