Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Gradient Flow Evolution for 3D Fusion From a Single Depth Sensor

Full metadata record
DC FieldValueLanguage
dc.contributor.authorKang, Jiwoo-
dc.contributor.authorLee, Seongmin-
dc.contributor.authorJang, Mingyu-
dc.contributor.authorLee, Sanghoon-
dc.date.accessioned2022-04-26T02:40:01Z-
dc.date.available2022-04-26T02:40:01Z-
dc.date.created2022-04-08-
dc.date.issued2022-04-
dc.identifier.issn1051-8215-
dc.identifier.urihttps://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/151304-
dc.description.abstractWe 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.language영어-
dc.language.isoen-
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)-
dc.titleGradient Flow Evolution for 3D Fusion From a Single Depth Sensor-
dc.typeArticle-
dc.contributor.affiliatedAuthorKang, Jiwoo-
dc.identifier.doi10.1109/tcsvt.2021.3089695-
dc.identifier.scopusid2-s2.0-85112167594-
dc.identifier.wosid000778973700042-
dc.identifier.bibliographicCitationIEEE Transactions on Circuits and Systems for Video Technology, v.32, no.4, pp.2211 - 2225-
dc.relation.isPartOfIEEE Transactions on Circuits and Systems for Video Technology-
dc.citation.titleIEEE Transactions on Circuits and Systems for Video Technology-
dc.citation.volume32-
dc.citation.number4-
dc.citation.startPage2211-
dc.citation.endPage2225-
dc.type.rimsART-
dc.description.journalClass1-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.subject.keywordPlusLEVEL SET EVOLUTION-
dc.subject.keywordPlusSCENE FLOW-
dc.subject.keywordPlusREGISTRATION-
dc.subject.keywordPlusSTEREO-
dc.subject.keywordPlusREINITIALIZATION-
dc.subject.keywordPlusOPTIMIZATION-
dc.subject.keywordPlusSPARSE-
dc.subject.keywordPlusFIELDS-
dc.subject.keywordPlusSHAPE-
dc.subject.keywordAuthorThree-dimensional displays-
dc.subject.keywordAuthorSurface reconstruction-
dc.subject.keywordAuthorPipelines-
dc.subject.keywordAuthorStrain-
dc.subject.keywordAuthorCameras-
dc.subject.keywordAuthorReliability-
dc.subject.keywordAuthorReal-time systems-
dc.subject.keywordAuthor3D reconstruction-
dc.subject.keywordAuthorsigned distance field-
dc.subject.keywordAuthorimplicit representation-
dc.subject.keywordAuthornon-rigid deformation-
dc.subject.keywordAuthorincremental reconstruction-
dc.identifier.urlhttps://ieeexplore.ieee.org/document/9456855?arnumber=9456855&SID=EBSCO:edseee-
Files in This Item
Go to Link
Appears in
Collections
ICT융합공학부 > IT공학전공 > 1. Journal Articles

qrcode

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

Related Researcher

Researcher Kang, Jiwoo photo

Kang, Jiwoo
ICT융합공학부 (IT공학전공)
Read more

Altmetrics

Total Views & Downloads

BROWSE