Leveraging Stereo Prior for Generalizable Novel-View Synthesis
- Title
- Leveraging Stereo Prior for Generalizable Novel-View Synthesis
- Authors
- 이해찬
- Date Issued
- 2024
- 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.
- URI
- http://postech.dcollection.net/common/orgView/200000733307
https://oasis.postech.ac.kr/handle/2014.oak/123405
- Article Type
- Thesis
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.