Confidence-Based Large-Scale Dense Multi-View Stereo

doi:10.1109/TIP.2020.2999853

	Confidence-Based Large-Scale Dense Multi-View Stereo
	Li, Zhaoxin 1,2; Zuo, Wangmeng 3; Wang, Zhaoqi 1; Zhang, Lei 2
	2020
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	29 页码:7176-7191
摘要	Albeit remarkable progress has been made to improve the accuracy and completeness of multi-view stereo (MVS), existing methods still suffer from either sparse reconstructions of low-textured surfaces or heavy computational burden. In this paper, we propose a Confidence-based Large-scale Dense Multi-view Stereo (CLD-MVS) method for high resolution imagery. Firstly, we formulate MVS as a multi-view depth estimation problem, and employ a normal-aware efficient PatchMatch stereo to estimate the initial depth and normal map for each reference view. A self-supervised deep learning method is then developed to predict the spatial confidence for multi-view depth maps, which is combined with cross-view consistency to generate the ground control points. Subsequently, a confidence-driven and boundary-aware interpolation scheme using static and dynamic guidance is adopted to synthesize dense depth and normal maps. Finally, a refinement procedure which leverages synthesized depth and normal as prior is conducted to estimate cross-view consistent surface. Experiments show that the proposed CLD-MVS method achieves high geometric completeness while preserving fine-scale details. In particular, it has ranked No. 1 on the ETH3D high-resolution MVS benchmark in terms of F-1-score.
关键词	Multi-view stereo confidence large-scale interpolation static and dynamic guidance refinement
DOI	10.1109/TIP.2020.2999853
收录类别	SCI
语种	英语
资助项目	NVIDIA Corporation
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000546910100021
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：28[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/2XEOYT63/15089
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.Hong Kong Polytech Univ, Dept Comp, Hong Kong, Peoples R China 3.Harbin Inst Technol, Sch Comp Sci & Technol, Harbin 150001, Peoples R China
推荐引用方式 GB/T 7714	Li, Zhaoxin,Zuo, Wangmeng,Wang, Zhaoqi,et al. Confidence-Based Large-Scale Dense Multi-View Stereo[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:7176-7191.
APA	Li, Zhaoxin,Zuo, Wangmeng,Wang, Zhaoqi,&Zhang, Lei.(2020).Confidence-Based Large-Scale Dense Multi-View Stereo.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,7176-7191.
MLA	Li, Zhaoxin,et al."Confidence-Based Large-Scale Dense Multi-View Stereo".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):7176-7191.