Detailed Information

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

Visual-Inertial Odometry Priors for Bundle-Adjusting Neural Radiance Fields

Full metadata record
DC Field Value Language
dc.contributor.authorKim, Hyunjin-
dc.contributor.authorSong, Minkyeong-
dc.contributor.authorLee, Daekyeong-
dc.contributor.authorKim, Pyojin-
dc.date.accessioned2023-11-08T07:48:30Z-
dc.date.available2023-11-08T07:48:30Z-
dc.date.issued2022-11-
dc.identifier.issn1598-7833-
dc.identifier.issn2642-3901-
dc.identifier.urihttps://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/152285-
dc.description.abstractWe present bundle-adjusting Neural Radiance Fields (BARF) with motion priors. Neural Radiance Field (NeRF) has opened up tremendous potential for neural volume rendering and 3D scene representations in recognition of their ability to synthesize photo-realistic novel views. BARF mitigates NeRF's reliance on accurate 6-DoF camera poses, enabling scene learning with inaccurate camera poses. However, initializing estimates far from an optimal solution, such as BARF, can easily fall into local minima. We utilize Visual-Inertial Odometry Motion Priors to the BARF, which jointly optimizes 3D scene representations and camera poses, providing higher accuracy in view synthesis and a more stable motion estimate. The proposed method achieves results that outperform original BARF in real-world data, demonstrating the effectiveness of motion priors to knowledge use. © 2022 ICROS.-
dc.format.extent6-
dc.language영어-
dc.language.isoENG-
dc.publisherIEEE Computer Society-
dc.titleVisual-Inertial Odometry Priors for Bundle-Adjusting Neural Radiance Fields-
dc.typeArticle-
dc.publisher.location미국-
dc.identifier.doi10.23919/ICCAS55662.2022.10003959-
dc.identifier.scopusid2-s2.0-85146585453-
dc.identifier.bibliographicCitationInternational Conference on Control, Automation and Systems, v.2022-November, pp 1131 - 1136-
dc.citation.titleInternational Conference on Control, Automation and Systems-
dc.citation.volume2022-November-
dc.citation.startPage1131-
dc.citation.endPage1136-
dc.type.docTypeConference Paper-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscopus-
dc.subject.keywordAuthorNeural Radiance Fields-
dc.subject.keywordAuthorNeural Rendering-
dc.subject.keywordAuthorView Synthesis-
dc.subject.keywordAuthorVisual-Inertial Odometry (VIO)-
dc.identifier.urlhttps://ieeexplore.ieee.org/document/10003959-
Files in This Item
Go to Link
Appears in
Collections
공과대학 > 기계시스템학부 > 1. Journal Articles

qrcode

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

Altmetrics

Total Views & Downloads

BROWSE