Using scale-equivariant CNN to enhance scale robustness in feature matching

被引:0
|
作者
Liao, Yun [1 ,2 ,3 ]
Liu, Peiyu [1 ,3 ]
Wu, Xuning [1 ,3 ]
Pan, Zhixuan [1 ,3 ]
Zhu, Kaijun [2 ]
Zhou, Hao [2 ]
Liu, Junhui [1 ,3 ]
Duan, Qing [1 ,3 ]
机构
[1] Yunnan Univ, Natl Pilot Sch Software, Kunming 650106, Yunnan, Peoples R China
[2] Yunnan Lanyi Network Technol Co, Kunming 650000, Yunnan, Peoples R China
[3] Yunnan Key Lab Software Engn, Kunming, Yunnan, Peoples R China
来源
VISUAL COMPUTER | 2024年 / 40卷 / 10期
关键词
Image matching; Feature matching; Scale-equivariance; Transformer;
D O I
10.1007/s00371-024-03389-0
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Image matching is an important task in computer vision. The detector-free dense matching method is an important research direction of image matching due to its high accuracy and robustness. The classical detector-free image matching methods utilize convolutional neural networks to extract features and then match them. Due to the lack of scale equivariance in CNNs, this method often exhibits poor matching performance when the images to be matched undergo significant scale variations. However, large-scale variations are very common in practical problems. To solve the above problem, we propose SeLFM, a method that combines scale equivariance and the global modeling capability of transformer. The two main advantages of this method are scale-equivariant CNNs can extract scale-equivariant features, while transformer also brings global modeling capability. Experiments prove that this modification improves the performance of the matcher in matching image pairs with large-scale variations and does not affect the general matching performance of the matcher. The code will be open-sourced at this link: https://github.com/LiaoYun0x0/SeLFM/tree/main
引用
收藏
页码:7307 / 7322
页数:16
相关论文
共 50 条
  • [41] Scale estimation of objects using template matching
    Gaxiola, Leopoldo N.
    Diaz-Ramirez, Victor H.
    Tapia, Juan J.
    OPTICS AND PHOTONICS FOR INFORMATION PROCESSING X, 2016, 9970
  • [42] Robust Feature Matching via Multi-scale Grid Structure
    Li, Yanping
    Huang, Qian
    Liu, Yizhang
    Huang, Yuan
    Sun, Xiaoqing
    2019 IEEE INTL CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, BIG DATA & CLOUD COMPUTING, SUSTAINABLE COMPUTING & COMMUNICATIONS, SOCIAL COMPUTING & NETWORKING (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2019), 2019, : 1187 - 1193
  • [43] Image detection scale-invariant feature transform algorithm based on feature matching improves image matching accuracy
    Guo, Shuli
    Han, Lina
    Hao, Xiaoting
    JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2017, 70 (16) : C10 - C10
  • [44] Recognition of fatigue and severe sliding wear particles using a CNN model with multi-scale feature extractor
    Liu, Xinliang
    Cheng, Liang
    Chen, Guoning
    Wang, Xiaolei
    Wang, Jingqiu
    INDUSTRIAL LUBRICATION AND TRIBOLOGY, 2022, 74 (07) : 884 - 891
  • [45] A note on the equivariant estimation of an exponential scale using progressively censored data
    Madi, Mohamed T.
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2010, 140 (06) : 1437 - 1440
  • [46] SCALE INVARIANT FEATURE MATCHING USING ROTATION-INVARIANT DISTANCE FOR REMOTE SENSING IMAGE REGISTRATION
    Li, Qiaoliang
    Zhang, Huisheng
    Wang, Tianfu
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2013, 27 (02)
  • [47] Stereo Matching Using Multi-Level Cost volume and Multi-Scale Feature Constancy
    Liang, Zhengfa
    Guo, Yulan
    Feng, Yiliu
    Chen, Wei
    Qiao, Linbo
    Zhou, Li
    Zhang, Jianfeng
    Liu, Hengzhu
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (01) : 300 - 315
  • [48] The robustness design of templates of CNN for detecting inner corners of object in gray-scale images
    Ming, L
    Min, LQ
    2004 INTERNATIONAL CONFERENCE ON COMMUNICATION, CIRCUITS, AND SYSTEMS, VOLS 1 AND 2: VOL 1: COMMUNICATION THEORY AND SYSTEMS - VOL 2: SIGNAL PROCESSING, CIRCUITS AND SYSTEMS, 2004, : 1090 - 1093
  • [49] Robust Faster R-CNN: Increasing Robustness to Occlusions and Multi-scale Objects
    Zhou, Tao
    Li, Zhixin
    Zhang, Canlong
    TRENDS AND APPLICATIONS IN KNOWLEDGE DISCOVERY AND DATA MINING: PAKDD 2019 WORKSHOPS, 2019, 11607 : 298 - 310
  • [50] Spatial Feature Extraction for Hyperspectral Image Classification Based on Multi-scale CNN
    Song, Haifeng
    Yang, Weiwei
    Journal of Computers (Taiwan), 2020, 31 (04) : 174 - 186