Please use this identifier to cite or link to this item: https://dspace.crs4.it/jspui/handle/1138/14
DC FieldValueLanguage
dc.contributor.authorPintore, Giovannien_US
dc.contributor.authorAgus, Marcoen_US
dc.contributor.authorGobbetti, Enricoen_US
dc.date.accessioned2020-11-02T12:53:05Z-
dc.date.available2020-11-02T12:53:05Z-
dc.date.issued2020-11-
dc.identifier.urihttps://dspace.crs4.it/jspui/handle/1138/14-
dc.description.abstractWe introduce a novel end-to-end approach to predict a 3D room layout from a single panoramic image. Compared to recent state-of-the-art works, our method is not limited to Manhattan World environments, and can reconstruct rooms bounded by vertical walls that do not form right angles or are curved - i.e., Atlanta World models. In our approach, we project the original gravity-aligned panoramic image on two horizontal planes, one above and one below the camera. This representation encodes all the information needed to recover the Atlanta World 3D bounding surfaces of the room in the form of a 2D room footprint on the floor plan and a room height. To predict the 3D layout, we propose an encoder-decoder neural network architecture, leveraging Recurrent Neural Networks (RNNs) to capture long-range geometric patterns, and exploiting a customized training strategy based on domain-specific knowledge. The experimental results demonstrate that our method outperforms state-of-the-art solutions in prediction accuracy, in particular in cases of complex wall layouts or curved wall footprints.en_US
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relationAdvanced Visual and Geometric Computing for 3D Capture, Display, and Fabricationen_US
dc.relationAMACen_US
dc.relationTDMen_US
dc.relationVIGECLABen_US
dc.relation.ispartofLNCSen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subject3D floor plan recoveryen_US
dc.subjectpanoramic imagesen_US
dc.subject360 imagesen_US
dc.subjectdata-driven reconstructionen_US
dc.subjectstructured indoor reconstructionen_US
dc.subjectindoor panoramaen_US
dc.subjectroom layout estimationen_US
dc.subjectholistic scene reconstructionen_US
dc.subjectvisual computingen_US
dc.titleAtlantaNet: Inferring the 3D Indoor Layout from a Single 360 Image beyond the Manhattan World Assumptionen_US
dc.typeresearch articleen_US
dc.relation.conferenceECCV 2020en_US
dc.relation.publicationComputer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIIIen_US
dc.identifier.doi10.1007/978-3-030-58598-3_26-
dc.contributor.affiliationCRS4en_US
dc.contributor.affiliationHBKUen_US
dc.contributor.affiliationCRS4en_US
dc.relation.isbn978-3-030-58597-6en_US
dc.relation.doi10.1007/978-3-030-58598-3en_US
dc.description.volume12353en_US
dc.description.startpage432en_US
dc.description.endpage448en_US
dc.relation.grantno813170en_US
dc.relation.grantnoPOR FESR 2014-2020en_US
dc.relation.grantnoPOR FESR 2014-2020en_US
dc.relation.grantnoPOR FESR 2014-2020en_US
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.openairetyperesearch article-
item.cerifentitytypePublications-
item.grantfulltextopen-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
crisitem.author.deptCRS4-
crisitem.author.orcid0000-0003-0831-2458-
crisitem.project.funderEC-
crisitem.project.projectURLwww.evocation.eu-
crisitem.project.fundingProgramH2020-
crisitem.project.openAireinfo:eu-repo/grantAgreement/EC/H2020/813170-
Appears in Collections:CRS4 publications
Files in This Item:
File Description SizeFormat
eccv2020-atlantanet.pdfAcceoted version10,45 MBAdobe PDFView/Open
Show simple item record

Page view(s)

21
checked on Nov 11, 2020

Google ScholarTM

Check

Altmetric

Altmetric


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