Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, JunYong | - |
dc.contributor.author | Lee, SeokYeong | - |
dc.contributor.author | Park, Haesol | - |
dc.contributor.author | Jung, Seung-Won | - |
dc.contributor.author | Kim, Ig-Jae | - |
dc.contributor.author | Cho, Junghyun | - |
dc.date.accessioned | 2024-01-12T02:45:56Z | - |
dc.date.available | 2024-01-12T02:45:56Z | - |
dc.date.created | 2023-11-17 | - |
dc.date.issued | 2023-06 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | https://pubs.kist.re.kr/handle/201004/76425 | - |
dc.description.abstract | We 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.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation | - |
dc.type | Conference | - |
dc.identifier.doi | 10.1109/CVPR52729.2023.00811 | - |
dc.description.journalClass | 1 | - |
dc.identifier.bibliographicCitation | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.8392 - 8401 | - |
dc.citation.title | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) | - |
dc.citation.startPage | 8392 | - |
dc.citation.endPage | 8401 | - |
dc.citation.conferencePlace | US | - |
dc.citation.conferencePlace | Vancouver, CANADA | - |
dc.citation.conferenceDate | 2023-06-17 | - |
dc.relation.isPartOf | 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | - |
dc.identifier.wosid | 001062522100038 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.