Gradient Flow Evolution for 3D Fusion From a Single Depth Sensor
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kang, Jiwoo | - |
dc.contributor.author | Lee, Seongmin | - |
dc.contributor.author | Jang, Mingyu | - |
dc.contributor.author | Lee, Sanghoon | - |
dc.date.accessioned | 2022-04-26T02:40:01Z | - |
dc.date.available | 2022-04-26T02:40:01Z | - |
dc.date.issued | 2022-04 | - |
dc.identifier.issn | 1051-8215 | - |
dc.identifier.issn | 1558-2205 | - |
dc.identifier.uri | https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/151304 | - |
dc.description.abstract | We present a novel real-time framework for non-rigid 3D reconstruction that is robust to noise, camera poses, and large deformation from a single depth camera. KinectFusion has achieved high-quality 3D object reconstructions in real-time by implicitly representing an object’s surface with a signed distance field (SDF) representation from a single depth camera. Many studies for incremental reconstruction have been presented since then, with the surface estimation improving over time. Previous works primarily focused on improving conventional SDF matching and deformation schemes. In contrast to these works, the proposed framework tackles the problem of temporal inconsistency caused by SDF approximation and fusion to manipulate SDFs and reconstruct a target more accurately over time. In our reconstruction pipeline, we introduce a refinement evolution method, where an erroneous SDF from a depth sensor is recovered more accurately in a few iterations by propagating erroneous SDF values from the surface. Reliable gradients of refined SDFs enable more accurate non-rigid tracking of a target object. Furthermore, we propose a level-set evolution for SDF fusion, enabling SDFs to be manipulated stably in the reconstruction pipeline over time. The proposed methods are fully parallelizable and can be executed in real-time. Q | - |
dc.format.extent | 15 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | - |
dc.title | Gradient Flow Evolution for 3D Fusion From a Single Depth Sensor | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1109/tcsvt.2021.3089695 | - |
dc.identifier.scopusid | 2-s2.0-85112167594 | - |
dc.identifier.wosid | 000778973700042 | - |
dc.identifier.bibliographicCitation | IEEE Transactions on Circuits and Systems for Video Technology, v.32, no.4, pp 2211 - 2225 | - |
dc.citation.title | IEEE Transactions on Circuits and Systems for Video Technology | - |
dc.citation.volume | 32 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 2211 | - |
dc.citation.endPage | 2225 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | LEVEL SET EVOLUTION | - |
dc.subject.keywordPlus | SCENE FLOW | - |
dc.subject.keywordPlus | REGISTRATION | - |
dc.subject.keywordPlus | STEREO | - |
dc.subject.keywordPlus | REINITIALIZATION | - |
dc.subject.keywordPlus | OPTIMIZATION | - |
dc.subject.keywordPlus | SPARSE | - |
dc.subject.keywordPlus | FIELDS | - |
dc.subject.keywordPlus | SHAPE | - |
dc.subject.keywordAuthor | Three-dimensional displays | - |
dc.subject.keywordAuthor | Surface reconstruction | - |
dc.subject.keywordAuthor | Pipelines | - |
dc.subject.keywordAuthor | Strain | - |
dc.subject.keywordAuthor | Cameras | - |
dc.subject.keywordAuthor | Reliability | - |
dc.subject.keywordAuthor | Real-time systems | - |
dc.subject.keywordAuthor | 3D reconstruction | - |
dc.subject.keywordAuthor | signed distance field | - |
dc.subject.keywordAuthor | implicit representation | - |
dc.subject.keywordAuthor | non-rigid deformation | - |
dc.subject.keywordAuthor | incremental reconstruction | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9456855?arnumber=9456855&SID=EBSCO:edseee | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Sookmyung Women's University. Cheongpa-ro 47-gil 100 (Cheongpa-dong 2ga), Yongsan-gu, Seoul, 04310, Korea02-710-9127
Copyright©Sookmyung Women's University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.