NeRF-based Polarimetric Multi-view Stereo

doi:10.1016/j.patcog.2024.111036

	NeRF-based Polarimetric Multi-view Stereo
	Cao, Jiakai 1; Yuan, Zhenlong 1; Mao, Tianlu 1; Wang, Zhaoqi 1; Li, Zhaoxin 2,3
	2025-02-01
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
卷号	158 页码:14
摘要	In this paper, we introduce NeRF-based Polarimetric Multi-view Stereo (NPMVS), a novel 3D reconstruction method that combines the advantages of neural radiance field (NeRF) and shape-from-polarization (SfP) address the challenge posed by textureless areas while preserving the fine-scale geometric details. Our method first leverages neural rendering to yield depth priors for each input view, subsequently estimates more accurate depths and normals using polarimetric refinement. We further introduce a pixel-wise depth rectification process to address the scaling problem inherent to the polarimetric refinement procedure. In addition, we contribute new realistic pBRDF-based multi-view synthetic dataset, comprised of RGB and polarization images rendered under real-world lighting conditions, which will serve as a valuable resource for future research in this field. Experimental evaluations on both synthetic and real-world datasets validate the superiority of NPMVS, demonstrating its advantage over other state-of-the-art multi-view stereo and shape-from-polarization methods.
关键词	Multi-view stereo Neural radiance fields Shape-from-polarization 3D reconstruction
DOI	10.1016/j.patcog.2024.111036
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62172392] ; Beijing Smart Agriculture Innova-tion Consortium Project[BAIC10-2024] ; Innovation Research Program of ICT[E261070]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001328179900001
出版者	ELSEVIER SCI LTD
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39566
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Zhaoxin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Chinese Acad Agr Sci, Agr Informat Inst, Beijing 100081, Peoples R China 3.Minist Agr & Rural Affairs, Key Lab Agr Big Data, Beijing 100081, Peoples R China
推荐引用方式 GB/T 7714	Cao, Jiakai,Yuan, Zhenlong,Mao, Tianlu,et al. NeRF-based Polarimetric Multi-view Stereo[J]. PATTERN RECOGNITION,2025,158:14.
APA	Cao, Jiakai,Yuan, Zhenlong,Mao, Tianlu,Wang, Zhaoqi,&Li, Zhaoxin.(2025).NeRF-based Polarimetric Multi-view Stereo.PATTERN RECOGNITION,158,14.
MLA	Cao, Jiakai,et al."NeRF-based Polarimetric Multi-view Stereo".PATTERN RECOGNITION 158(2025):14.