Coarse to fine image matching by mining matchable regions and geometric cues

IF 3.3 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Pattern Recognition Letters Pub Date : 2025-06-26 DOI:10.1016/j.patrec.2025.06.009

Qingqun Kong , Zhili Qiu , Yiming Zheng , Kehu Yang , Bin Fan

{"title":"Coarse to fine image matching by mining matchable regions and geometric cues","authors":"Qingqun Kong , Zhili Qiu , Yiming Zheng , Kehu Yang , Bin Fan","doi":"10.1016/j.patrec.2025.06.009","DOIUrl":null,"url":null,"abstract":"<div><div>Detector-free image matchers have shown promising results in handling challenging cases of image matching. Their coarse-to-fine matching pipeline is particularly prone to incorrect matches in the coarse matching stage. This paper proposes to enhance coarse features by focusing attention learning more on matchable regions and to improve coarse match accuracy by exploring the geometric consistency among matches. For the enhanced feature extraction module, a regional attention mechanism is used in addition to the widely used global attention for self-/cross-feature interaction. For the feature matching module, a second-order geometric relation-induced matching confidence is proposed. These two modules respectively explore appearance and geometric cues to improve the quality of coarse matches and can be seamlessly integrated into existing coarse-to-fine matching pipelines. The effectiveness of the proposed method has been extensively validated on two popular coarse-to-fine matching pipelines (LoFTR and ASpanFormer), demonstrating improved performance on various image matching downstream tasks.</div></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":"196 ","pages":"Pages 289-295"},"PeriodicalIF":3.3000,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pattern Recognition Letters","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167865525002375","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Detector-free image matchers have shown promising results in handling challenging cases of image matching. Their coarse-to-fine matching pipeline is particularly prone to incorrect matches in the coarse matching stage. This paper proposes to enhance coarse features by focusing attention learning more on matchable regions and to improve coarse match accuracy by exploring the geometric consistency among matches. For the enhanced feature extraction module, a regional attention mechanism is used in addition to the widely used global attention for self-/cross-feature interaction. For the feature matching module, a second-order geometric relation-induced matching confidence is proposed. These two modules respectively explore appearance and geometric cues to improve the quality of coarse matches and can be seamlessly integrated into existing coarse-to-fine matching pipelines. The effectiveness of the proposed method has been extensively validated on two popular coarse-to-fine matching pipelines (LoFTR and ASpanFormer), demonstrating improved performance on various image matching downstream tasks.

查看原文本刊更多论文

通过挖掘匹配区域和几何线索进行粗到细的图像匹配

无检测器图像匹配器在处理具有挑战性的图像匹配案例中显示出了有希望的结果。它们的粗到精匹配管道在粗匹配阶段特别容易出现不正确的匹配。本文提出通过集中学习匹配区域来增强粗特征，通过探索匹配之间的几何一致性来提高粗匹配精度。对于增强的特征提取模块，除了广泛使用的全局注意机制外，还采用了区域注意机制进行自/跨特征交互。对于特征匹配模块，提出了二阶几何关系诱导的匹配置信度。这两个模块分别探索外观和几何线索，以提高粗匹配的质量，并可以无缝集成到现有的粗到精匹配管道中。该方法的有效性已经在两种流行的粗到精匹配管道（LoFTR和ASpanFormer）上得到了广泛的验证，在各种图像匹配下游任务上显示出改进的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Pattern Recognition Letters 工程技术-计算机：人工智能

CiteScore

12.40

自引率

5.90%

发文量

287

审稿时长

9.1 months

期刊介绍： Pattern Recognition Letters aims at rapid publication of concise articles of a broad interest in pattern recognition. Subject areas include all the current fields of interest represented by the Technical Committees of the International Association of Pattern Recognition, and other developing themes involving learning and recognition.