Loading [a11y]/accessibility-menu.js
Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching | IEEE Journals & Magazine | IEEE Xplore

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


Abstract:

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 meth...Show More

Abstract:

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.
Page(s): 1335 - 1348
Date of Publication: 28 September 2022

ISSN Information:

Funding Agency:

Citations are not available for this document.

I. Introduction

Establishing pixel-level correspondences between two images is an essential basis for a wide range of computer vision tasks such as visual localization [1], [2], 3D scene reconstruction [3] and simultaneous localization and mapping (SLAM) [4]. Such correspondences are usually estimated by sparse local feature extraction and matching [5], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16]. A local feature consists of a keypoint and a descriptor. But the scale invariance of both existing keypoint detectors and descriptors is not enough to deal with large scale changes [17]. Few inlier correspondences can be established by matching local features under the circumstances of large scale changes in images, which is called as the scale problem of local features in this paper. If the scale difference between two images is small, we call that the two images are at related scale levels in scale space [18], [19].

Cites in Papers - |

Cites in Papers - IEEE (12)

Select All
1.
Yubing Wu, Danfeng Sun, Mingjia Zhang, Jianyong Zhao, Huifeng Wu, "Beetle Swarm With Constrained Lévy Flight for Image Matching", IEEE Transactions on Automation Science and Engineering, vol.22, pp.3366-3376, 2025.
2.
Jinjing Chen, Hao Zhu, Shiqiang Dai, Sin-Chi Kuok, "A Robust Feature Matching Method based on Semantic Geometric Constraints", 2024 China Automation Congress (CAC), pp.3286-3291, 2024.
3.
Gongxin Yao, Yixin Xuan, Yiwei Chen, Yu Pan, "Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registration", IEEE Sensors Journal, vol.24, no.20, pp.33826-33837, 2024.
4.
Changcai Yang, Xiaojie Li, Jiayi Ma, Fengyuan Zhuang, Lifang Wei, Riqing Chen, Guodong Chen, "CGR-Net: Consistency Guided ResFormer for Two-View Correspondence Learning", IEEE Transactions on Circuits and Systems for Video Technology, vol.34, no.12, pp.12450-12465, 2024.
5.
Zhunga Liu, Huandong Li, Zuowei Zhang, Yanyi Lyu, Jiexuan Xiong, "Multimodal Absolute Visual Localization for Unmanned Aerial Vehicles", IEEE Transactions on Vehicular Technology, vol.73, no.11, pp.16402-16415, 2024.
6.
Yicheng Lin, Yunlong Jiang, Xujia Jiao, Bin Han, "Learned Good Features to Track", IEEE Transactions on Circuits and Systems for Video Technology, vol.34, no.11, pp.10692-10703, 2024.
7.
Bingxi Liu, Yujie Fu, Feng Lu, Jinqiang Cui, Yihong Wu, Hong Zhang, "NPR: Nocturnal Place Recognition Using Nighttime Translation in Large-Scale Training Procedures", IEEE Journal of Selected Topics in Signal Processing, vol.18, no.3, pp.368-379, 2024.
8.
Mingwei Cao, Qi Yan, Ye Yu, Haifeng Zhao, Zhihan Lyu, "MLV: Robust Image Matching via Multilayer Verification", IEEE Sensors Journal, vol.24, no.9, pp.14454-14470, 2024.
9.
Zizhuo Li, Chunbao Su, Fan Fan, Jun Huang, Jiayi Ma, "MC-Net: Integrating Multi-Level Geometric Context for Two-View Correspondence Learning", IEEE Transactions on Circuits and Systems for Video Technology, vol.34, no.8, pp.7550-7565, 2024.
10.
Rongtao Xu, Changwei Wang, Shibiao Xu, Weiliang Meng, Yuyang Zhang, Bin Fan, Xiaopeng Zhang, "DomainFeat: Learning Local Features With Domain Adaptation", IEEE Transactions on Circuits and Systems for Video Technology, vol.34, no.1, pp.46-59, 2024.
11.
Bo Jiang, Shuxian Luo, Xiao Wang, Chuanfu Li, Jin Tang, "AMatFormer: Efficient Feature Matching via Anchor Matching Transformer", IEEE Transactions on Multimedia, vol.26, pp.1504-1515, 2024.
12.
Jiahuan Yu, Jiahao Chang, Jianfeng He, Tianzhu Zhang, Jiyang Yu, Feng Wu, "Adaptive Spot-Guided Transformer for Consistent Local Feature Matching", 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.21898-21908, 2023.

Cites in Papers - Other Publishers (5)

1.
Yanhai Tan, Peng Ji, Yunzhou Zhang, Fawei Ge, Shangdong Zhu, "Learning robust representation and sequence constraint for retrieval-based long-term visual place recognition", Engineering Applications of Artificial Intelligence, vol.138, pp.109425, 2024.
2.
Yan Zhou, Jinding Gao, Xiaoping Liu, "A unified feature-motion consistency framework for robust image matching", ISPRS Journal of Photogrammetry and Remote Sensing, vol.218, pp.368, 2024.
3.
Zhiyuan Gan, Li Teng, Ying Chang, Xinyang Feng, Mengnan Gao, Xinwen Gao, "A Multi-Information Fusion Method for Repetitive Tunnel Disease Detection", Sustainability, vol.16, no.10, pp.4285, 2024.
4.
Yanzhe Chen, Jiahuan Zhou, Yuxin Peng, "SPIRIT: Style-guided Patch Interaction for Fashion Image Retrieval with Text Feedback", ACM Transactions on Multimedia Computing, Communications, and Applications, 2024.
5.
Xiangzeng Liu, Xueling Xu, Xiaodong Zhang, Qiguang Miao, Lei Wang, Liang Chang, Ruyi Liu, "SRTPN: Scale and Rotation Transform Prediction Net for Multimodal Remote Sensing Image Registration", Remote Sensing, vol.15, no.14, pp.3469, 2023.

References

References is not available for this document.