Multiview Feature Aggregation for Facade Parsing

doi:10.1109/LGRS.2020.3035721

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 三维可视计算

	Multiview Feature Aggregation for Facade Parsing
	Ma, Wenguang 3; Xu, Shibiao 2; Ma, Wei 3; Zha, Hongbin 1
刊名	IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
	2022
卷号	19 页码:5
关键词	Semantics Image segmentation Feature extraction Training Three-dimensional displays Data models Computer architecture Facade parsing feature aggregation multiview wide baseline
ISSN号	1545-598X
DOI	10.1109/LGRS.2020.3035721
通讯作者	Ma, Wei(mawei@bjut.edu.cn)
英文摘要	Facade image parsing is essential to the semantic understanding and 3-D reconstruction of urban scenes. Considering the occlusion and appearance ambiguity in single-view images and the easy acquisition of multiple views, in this letter, we propose a multiview enhanced deep architecture for facade parsing. The highlight of this architecture is a cross-view feature aggregation module that can learn to choose and fuse useful convolutional neural network (CNN) features from nearby views to enhance the representation of a target view. Benefitting from the multiview enhanced representation, the proposed architecture can better deal with the ambiguity and occlusion issues. Moreover, our cross-view feature aggregation module can be straightforwardly integrated into existing single-image parsing frameworks. Extensive comparison experiments and ablation studies are conducted to demonstrate the good performance of the proposed method and the validity and transportability of the cross-view feature aggregation module.
资助项目	National Natural Science Foundation of China[61771026] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61971418] ; National Key Research and Development Program of China[2018YFB2100602] ; Open Research Fund of Key Laboratory of Space Utilization, Chinese Academy of Sciences[LSU-KFJJ-2020-04]
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000736769300025
资助机构	National Natural Science Foundation of China ; National Key Research and Development Program of China ; Open Research Fund of Key Laboratory of Space Utilization, Chinese Academy of Sciences
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/47310]
专题	模式识别国家重点实验室_三维可视计算
通讯作者	Ma, Wei
作者单位	1.Peking Univ, Sch Elect Engn & Comp Sci, Key Lab Machine Percept MOE, Beijing 100871, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
推荐引用方式 GB/T 7714	Ma, Wenguang,Xu, Shibiao,Ma, Wei,et al. Multiview Feature Aggregation for Facade Parsing[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2022,19:5.
APA	Ma, Wenguang,Xu, Shibiao,Ma, Wei,&Zha, Hongbin.(2022).Multiview Feature Aggregation for Facade Parsing.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,19,5.
MLA	Ma, Wenguang,et al."Multiview Feature Aggregation for Facade Parsing".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 19(2022):5.