Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching

doi:10.1109/TCSVT.2022.3210602

	Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching
	Fu Yujie1,2 ; Zhang Pengju1 ; Liu Bingxi2 ; Rong Zheng1 ; Wu Yihong1,2
发表期刊	IEEE Transactions on Circuits and Systems for Video Technology
ISSN	1558-2205
	2023
卷号	33 期号:3 页码:1335 - 1348
摘要	Most image matching methods perform poorly when encountering large scale changes in images. To solve this problem, we propose a Scale-Difference-Aware Image Matching method (SDAIM) that reduces image scale differences before local feature extraction, via resizing both images of an image pair according to an estimated scale ratio. In order to accurately estimate the scale ratio for the proposed SDAIM, we propose a Covisibility-Attention-Reinforced Matching module (CVARM) and then design a novel neural network, termed as Scale-Net, based on CVARM. The proposed CVARM can lay more stress on covisible areas within the image pair and suppress the distraction from those areas visible in only one image. Quantitative and qualitative experiments confirm that the proposed Scale-Net has higher scale ratio estimation accuracy and much better generalization ability compared with all the existing scale ratio estimation methods. Further experiments on image matching and relative pose estimation tasks demonstrate that our SDAIM and Scale-Net are able to greatly boost the performance of representative local features and state-of-the-art local feature matching methods.
关键词	Image Matching Large Scale Changes Scale Difference Reduction Scale Ratio Estimation Covisibility-attention-reinforced Matching Module
学科门类	工学::控制科学与工程
DOI	10.1109/TCSVT.2022.3210602
URL	查看原文
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61836015]
是否为代表性论文	是
七大方向——子方向分类	三维视觉
国重实验室规划方向分类	视觉信息处理
是否有论文关联数据集需要存交	否
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56567
专题	多模态人工智能系统全国重点实验室_机器人视觉
通讯作者	Wu Yihong
作者单位	1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Fu Yujie,Zhang Pengju,Liu Bingxi,et al. Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching[J]. IEEE Transactions on Circuits and Systems for Video Technology,2023,33(3):1335 - 1348.
APA	Fu Yujie,Zhang Pengju,Liu Bingxi,Rong Zheng,&Wu Yihong.(2023).Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching.IEEE Transactions on Circuits and Systems for Video Technology,33(3),1335 - 1348.
MLA	Fu Yujie,et al."Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching".IEEE Transactions on Circuits and Systems for Video Technology 33.3(2023):1335 - 1348.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Learning_to_Reduce_S（4879KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览