Image stitching via deep homography estimation

doi:10.1016/j.neucom.2021.03.099

	Image stitching via deep homography estimation
	Zhao, Qiang 1; Ma, Yike 1; Zhu, Chen 1; Yao, Chunfeng 2; Feng, Bailan 2; Dai, Feng 1
	2021-08-25
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	450 页码:219-229
摘要	Image stitching is a well-studied problem and has many applications in a variety of fields. Traditional feature based methods rely heavily on accurate localization or even distribution of hand-crafted features, and may fail for some difficult cases. Although there are robust deep learning based homography estimation or semantic alignment methods, their accuracies are not high enough for image stitching problem. In this paper, we present a deep neural network that estimates homography accurately enough for image stitching of images with small parallax. The key components of our network are feature maps with progressively increased resolution and matching cost volumes constructed in hybrid manner. Both of these designs are illustrated to be helpful for performance improvement. We also propose a new stitching oriented loss function that takes image contents into consideration. To train our network, we prepare a synthesized training dataset, the image pairs in which are more nature and similar to those of real world image stitching problem. Experimental results demonstrate that our method outperforms existing deep learning based methods and traditional feature based method in term of quantitative evaluation, visual stitching result and robustness. (c) 2021 Elsevier B.V. All rights reserved.
关键词	Image stitching Homography estimation Deep learning Alignment
DOI	10.1016/j.neucom.2021.03.099
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61702479] ; National Natural Science Foundation of China[61771458] ; Science and technology Innovation 2030[2018AAA0103000]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000660414000002
出版者	ELSEVIER
引用统计	被引频次：35[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/2XEOYT63/17600
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ma, Yike
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 2.Huawei Noahs Ark Lab, Hong Kong, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Qiang,Ma, Yike,Zhu, Chen,et al. Image stitching via deep homography estimation[J]. NEUROCOMPUTING,2021,450:219-229.
APA	Zhao, Qiang,Ma, Yike,Zhu, Chen,Yao, Chunfeng,Feng, Bailan,&Dai, Feng.(2021).Image stitching via deep homography estimation.NEUROCOMPUTING,450,219-229.
MLA	Zhao, Qiang,et al."Image stitching via deep homography estimation".NEUROCOMPUTING 450(2021):219-229.