DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, SJ | - |
dc.contributor.author | Hong, KS | - |
dc.date.accessioned | 2017-07-19T12:22:43Z | - |
dc.date.available | 2017-07-19T12:22:43Z | - |
dc.date.created | 2016-02-12 | - |
dc.date.issued | 2015-12-15 | - |
dc.identifier.issn | 0167-8655 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/35742 | - |
dc.description.abstract | In this paper, we propose a framework to recover a 3D cuboidal indoor scene with a novel detector-based semantic segmentation feature and a carefully-modified orientation map. We use those features to mimic the ability of humans to recognize a 3D layout from a single image. We define all the potentials in our model under a conditional random field formulation. Our experimental results show the effectiveness of our new features which complement the limitations of existing bottom-up geometric features while achieving the state-of-the-art layout accuracy on the indoor UIUC dataset. (C) 2015 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCIENCE BV | - |
dc.relation.isPartOf | PATTERN RECOGNITION LETTERS | - |
dc.title | Recovering an indoor 3D layout with top-down semantic segmentation from a single image | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/J.PATREC.2015.08.014 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION LETTERS, v.68, pp.70 - 75 | - |
dc.identifier.wosid | 000365181400011 | - |
dc.date.tcdate | 2019-03-01 | - |
dc.citation.endPage | 75 | - |
dc.citation.startPage | 70 | - |
dc.citation.title | PATTERN RECOGNITION LETTERS | - |
dc.citation.volume | 68 | - |
dc.contributor.affiliatedAuthor | Hong, KS | - |
dc.identifier.scopusid | 2-s2.0-84942253707 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.wostc | 2 | - |
dc.description.scptc | 2 | * |
dc.date.scptcdate | 2018-05-121 | * |
dc.type.docType | Article | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.