Conditional visibility aware view synthesis via parallel light fields

doi:10.1016/j.neucom.2024.127644

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Conditional visibility aware view synthesis via parallel light fields
	Shen, Yu1,2 ; Li, Yuke3,5 ; Liu, Yuhang 2; Wang, Yutong2 ; Chen, Long2,3 ; Wang, Fei-Yue1,2,4
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2024-07-01
卷号	588 页码:13
通讯作者	Li, Yuke(liyuke14@mails.ucas.ac.cn)
摘要	In the area of neural rendering -based novel view synthesis, illumination is important since shadows cast by objects under various light sources provide indications about their geometries and materials. However, due to high physical device complexity and simulation distortion, large-scale photorealistic multiple illumination multi -view datasets are difficult to obtain. In order to address this problem, a physical -virtual interactive parallel light fields based collection method is proposed in this paper. The physical part of parallel light fields is firstly used to capture 3D models and 2D images of objects under different lights. Then a Reakto-Sim adaptation module was proposed to enhance realism by estimating material characteristic. Instead of manually setting, the learned resulting material parameters are then utilized to initialize virtual engine blender for subsequent rendering and data collection. Besides, to better handle self -occlusion problem in the acquired parallel light fields dataset, a conditional visibility module is designed in modeling visibility of each sampling point along a sampling ray. Compared with the Neuray, by introducing Conditional Normalizing Flow, visibility are assumed as samples from some distribution due to the fact that visibilities along the ray should be monotonically decreasing and are within the range of [0 , 1] . The visibility are calculated in a data driven manner, which brings more flexibility. By pretraining the conditional visibility network in parallel light field dataset, experiments demonstrate that more photorealistic inputs improve Peak -Signal -Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) by 0.11% and 0.68% in validation dataset NeRF synthesis and LLFF. Besides, compared to Neuray, the proposed conditional visibility module is more flexible and get a PSNR improvement of 0.55 and 0.5 in NeRF synthesis and LLFF dataset, respectively.
关键词	Parallel theory Light fields Neural rendering View synthesis Conditional visibility Normalizing Flow
DOI	10.1016/j.neucom.2024.127644
关键词[WOS]	NEURAL RADIANCE FIELDS ; INTELLIGENCE ; NETWORK ; SYSTEM
收录类别	SCI
语种	英语
资助项目	Key Research and Developing Program 2020 of Guangzhou[202007050002] ; Developing Program of Guangdong Province[2020B090921003] ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV)
项目资助者	Key Research and Developing Program 2020 of Guangzhou ; Developing Program of Guangdong Province ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001229948200001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58419
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Li, Yuke
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Waytous Co Ltd, Beijing 100083, Peoples R China 4.Macau Univ Sci & Technol, Macao Inst Syst Engn, Macau 999078, Peoples R China 5.Northwestern Polytech Univ, Sch Software, Xian 710072, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Shen, Yu,Li, Yuke,Liu, Yuhang,et al. Conditional visibility aware view synthesis via parallel light fields[J]. NEUROCOMPUTING,2024,588:13.
APA	Shen, Yu,Li, Yuke,Liu, Yuhang,Wang, Yutong,Chen, Long,&Wang, Fei-Yue.(2024).Conditional visibility aware view synthesis via parallel light fields.NEUROCOMPUTING,588,13.
MLA	Shen, Yu,et al."Conditional visibility aware view synthesis via parallel light fields".NEUROCOMPUTING 588(2024):13.