NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Rendering

doi:10.1109/ICCP56744.2023.10233838

	NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Rendering
	Ziyu Wang1 ; Wei Yang 2; Junming Cao 3; Qiang Hu4 ; Lan Xu4 ; Junqing Yu 2; Jingyi Yu4
	2023-07-28
会议录名称	2023 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL PHOTOGRAPHY (ICCP)
ISSN	2164-9774
发表状态	已发表
DOI	10.1109/ICCP56744.2023.10233838
摘要	We present a novel Neural Refractive Field (NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front. Unlike prior arts that treat the reconstruction target as a single layer of the surface, NeReF is specifically formulated to recover a volumetric normal field with its corresponding density field. A query ray will be refracted by NeReF according to its accumulated refractive point and normal, and we employ the correspondences and uniqueness of refracted ray for NeReF optimization. We show NeReF, as a global optimization scheme, can more robustly tackle refraction distortions detrimental to traditional methods for correspondence matching. Furthermore, the continuous NeReF representation of wavefront enables view synthesis as well as normal integration. We validate our approach on both synthetic and real data and show it is particularly suitable for sparse multi-view acquisition. We hence build a small light field array and experiment on various surface shapes to demonstrate high fidelity NeReF reconstruction. © 2023 IEEE.
会议录编者/会议主办者	et al. ; KLA+ ; PI Imaging ; Snap Inc. ; Sony ; Ubicept
关键词	Computational Photography Fluid Reconstruction Implicit Representation
会议名称	15th IEEE International Conference on Computational Photography, ICCP 2023
会议地点	Madison, WI, USA
会议日期	28-30 July 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20234014830085
EI主题词	Wavefronts
EI分类号	723.5 Computer Applications ; 741.2 Vision ; 742.1 Photography ; 921.5 Optimization Techniques
原始文献类型	Conference article (CA)
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/333448
专题	信息科学与技术学院信息科学与技术学院_PI研究组_虞晶怡组信息科学与技术学院_博士生信息科学与技术学院_PI研究组_许岚组
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, 201210, China 2.Huazhong University of Science and Technology, Wuhan, 430074, China 3.Shanghai Advanced Research Institute and also with ShanghaiTech University, Shanghai, 201210, China 4.School of Information Science and Technology, ShanghaiTech University and also with the Shanghai Engineering Research Center of Intelligent Vision and Imaging, Shanghai, 201210, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Ziyu Wang,Wei Yang,Junming Cao,et al. NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Rendering[C]//et al., KLA+, PI Imaging, Snap Inc., Sony, Ubicept:Institute of Electrical and Electronics Engineers Inc.,2023.