DC Field | Value | Language |
---|---|---|
dc.contributor.author | 이해찬 | - |
dc.date.accessioned | 2024-05-10T16:38:51Z | - |
dc.date.available | 2024-05-10T16:38:51Z | - |
dc.date.issued | 2024 | - |
dc.identifier.other | OAK-2015-10453 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000733307 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/123405 | - |
dc.description | Master | - |
dc.description.abstract | In this thesis, we propose the first generalizable view synthesis approach that exploits stereo images. Since recent stereo matching has demonstrated accurate geometry prediction, we introduce stereo matching into novel-view synthesis for high-quality geometry reconstruction. To this end, this thesis proposes a novel framework, dubbed StereoNeRF, which integrates stereo matching into a NeRF-based generalizable view synthesis approach. StereoNeRF is equipped with three key components to effectively exploit stereo matching in novel-view synthesis: a stereo feature extractor, a depth-guided plane-sweeping, and a stereo depth loss. Moreover, we propose the StereoNVS dataset, the first multi-view dataset of stereo images, encompassing a wide variety of both real and synthetic scenes. Our experimental results demonstrate that StereoNeRF surpasses previous approaches in generalizable view synthesis. | - |
dc.language | eng | - |
dc.title | Leveraging Stereo Prior for Generalizable Novel-View Synthesis | - |
dc.type | Thesis | - |
dc.contributor.college | 인공지능대학원 | - |
dc.date.degree | 2024- 2 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.