There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 4113 | - |
dc.citation.number | 5 | - |
dc.citation.startPage | 4106 | - |
dc.citation.title | IEEE ROBOTICS AND AUTOMATION LETTERS | - |
dc.citation.volume | 9 | - |
dc.contributor.author | Jang, Jaehoon | - |
dc.contributor.author | Lee, Inha | - |
dc.contributor.author | Kim, Minje | - |
dc.contributor.author | Joo, Kyungdon | - |
dc.date.accessioned | 2024-05-03T10:35:17Z | - |
dc.date.available | 2024-05-03T10:35:17Z | - |
dc.date.created | 2024-04-23 | - |
dc.date.issued | 2024-05 | - |
dc.description.abstract | Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online signed distance fields (SDF) reconstruction framework in indoor scenes, especially under the Atlanta world (AW) assumption. Thus, we dub this incremental SDF reconstruction for AW as AiSDF. Within the online framework, we infer the underlying Atlanta structure of a given scene and then estimate planar surfel regions supporting the Atlanta structure. This Atlanta-aware surfel representation provides an explicit planar map for a given scene. In addition, based on these Atlanta planar surfel regions, we adaptively sample and constrain the structural regularity in the SDF reconstruction, which enables us to improve the reconstruction quality by maintaining a high-level structure while enhancing the details of a given scene. We evaluate the proposed AiSDF on the ScanNet and ReplicaCAD datasets, where we demonstrate that the proposed framework is capable of reconstructing fine details of objects implicitly, as well as structures explicitly in room-scale scenes. | - |
dc.identifier.bibliographicCitation | IEEE ROBOTICS AND AUTOMATION LETTERS, v.9, no.5, pp.4106 - 4113 | - |
dc.identifier.doi | 10.1109/LRA.2024.3375117 | - |
dc.identifier.issn | 2377-3766 | - |
dc.identifier.scopusid | 2-s2.0-85187366009 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/82271 | - |
dc.identifier.wosid | 001189370400004 | - |
dc.language | 영어 | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | AiSDF: Structure-Aware Neural Signed Distance Fields in Indoor Scenes | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Robotics | - |
dc.relation.journalResearchArea | Robotics | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Deep learning for visual perception | - |
dc.subject.keywordAuthor | mapping | - |
dc.subject.keywordAuthor | incremental learning | - |
dc.subject.keywordPlus | WORLD | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.