Full metadata record

DC Field Value Language
dc.contributor.authorChoi, JunYong-
dc.contributor.authorLee, SeokYeong-
dc.contributor.authorPark, Haesol-
dc.contributor.authorJung, Seung-Won-
dc.contributor.authorKim, Ig-Jae-
dc.contributor.authorCho, Junghyun-
dc.date.accessioned2024-01-12T02:45:56Z-
dc.date.available2024-01-12T02:45:56Z-
dc.date.created2023-11-17-
dc.date.issued2023-06-
dc.identifier.issn1063-6919-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/76425-
dc.description.abstractWe propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-view images provide a variety of information about the scene, multi-view images in object-level inverse rendering have been taken for granted. However, owing to the absence of multi-view HDR synthetic dataset, scene-level inverse rendering has mainly been studied using single-view image. We were able to successfully perform scene-level inverse rendering using multi-view images by expanding OpenRooms dataset and designing efficient pipelines to handle multi-view images, and splitting spatially-varying lighting. Our experiments show that the proposed method not only achieves better performance than single-view-based methods, but also achieves robust performance on unseen real-world scene. Also, our sophisticated 3D spatially-varying lighting volume allows for photorealistic object insertion in any 3D location.-
dc.languageEnglish-
dc.publisherIEEE COMPUTER SOC-
dc.titleMAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation-
dc.typeConference-
dc.identifier.doi10.1109/CVPR52729.2023.00811-
dc.description.journalClass1-
dc.identifier.bibliographicCitation2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.8392 - 8401-
dc.citation.title2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)-
dc.citation.startPage8392-
dc.citation.endPage8401-
dc.citation.conferencePlaceUS-
dc.citation.conferencePlaceVancouver, CANADA-
dc.citation.conferenceDate2023-06-17-
dc.relation.isPartOf2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)-
dc.identifier.wosid001062522100038-
Appears in Collections:
KIST Conference Paper > 2023
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

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

BROWSE