Image stitching via deep homography estimation

doi:10.1016/j.neucom.2021.03.099

	Image stitching via deep homography estimation
	Zhao, Qiang 2; Ma, Yike 2; Zhu, Chen 2; Yao, Chunfeng 1; Feng, Bailan 1; Dai, Feng 2
刊名	NEUROCOMPUTING
	2021-08-25
卷号	450 页码:219-229
关键词	Image stitching Homography estimation Deep learning Alignment
ISSN号	0925-2312
DOI	10.1016/j.neucom.2021.03.099
英文摘要	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.
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
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000660414000002
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17599]
专题	中国科学院计算技术研究所
通讯作者	Ma, Yike
作者单位	1.Huawei Noahs Ark Lab, Hong Kong, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, 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.