Generalizable Novel-View Synthesis using a Stereo Camera

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Haechan, Jin, Wonjoon, Baek, Seung-Hwan, Cho, Sunghyun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911847744012288
author Lee, Haechan
Jin, Wonjoon
Baek, Seung-Hwan
Cho, Sunghyun
author_facet Lee, Haechan
Jin, Wonjoon
Baek, Seung-Hwan
Cho, Sunghyun
contents In this paper, we propose the first generalizable view synthesis approach that specifically targets multi-view stereo-camera 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 paper 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-camera images, encompassing a wide variety of both real and synthetic scenes. Our experimental results demonstrate that StereoNeRF surpasses previous approaches in generalizable view synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2404_13541
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalizable Novel-View Synthesis using a Stereo Camera
Lee, Haechan
Jin, Wonjoon
Baek, Seung-Hwan
Cho, Sunghyun
Computer Vision and Pattern Recognition
In this paper, we propose the first generalizable view synthesis approach that specifically targets multi-view stereo-camera 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 paper 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-camera images, encompassing a wide variety of both real and synthetic scenes. Our experimental results demonstrate that StereoNeRF surpasses previous approaches in generalizable view synthesis.
title Generalizable Novel-View Synthesis using a Stereo Camera
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.13541