T-Net++: Effective Permutation-Equivariance Network for Two-View Correspondence Pruning.

Guobao Xiao, Xin Liu, Zhen Zhong, Xiaoqin Zhang, Jiayi Ma, Haibin Ling
{"title":"T-Net++: Effective Permutation-Equivariance Network for Two-View Correspondence Pruning.","authors":"Guobao Xiao, Xin Liu, Zhen Zhong, Xiaoqin Zhang, Jiayi Ma, Haibin Ling","doi":"10.1109/TPAMI.2024.3444457","DOIUrl":null,"url":null,"abstract":"<p><p>We propose a conceptually novel, flexible, and effective framework (named T-Net++) for the task of two-view correspondence pruning. T-Net++ comprises two unique structures: the \"-'' structure and the \"|'' structure. The \"-'' structure utilizes an iterative learning strategy to process correspondences, while the \"|'' structure integrates all feature information of the \"-'' structure and produces inlier weights. Moreover, within the \"|'' structure, we design a new Local-Global Attention Fusion module to fully exploit valuable information obtained from concatenating features through channel-wise and spatial-wise relationships. Furthermore, we develop a Channel-Spatial Squeeze-and-Excitation module, a modified network backbone that enhances the representation ability of important channels and correspondences through the squeeze-and-excitation operation. T-Net++ not only preserves the permutation-equivariance manner for correspondence pruning, but also gathers rich contextual information, thereby enhancing the effectiveness of the network. Experimental results demonstrate that T-Net++ outperforms other state-of-the-art correspondence pruning methods on various benchmarks and excels in two extended tasks.</p>","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TPAMI.2024.3444457","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/11/6 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

We propose a conceptually novel, flexible, and effective framework (named T-Net++) for the task of two-view correspondence pruning. T-Net++ comprises two unique structures: the "-'' structure and the "|'' structure. The "-'' structure utilizes an iterative learning strategy to process correspondences, while the "|'' structure integrates all feature information of the "-'' structure and produces inlier weights. Moreover, within the "|'' structure, we design a new Local-Global Attention Fusion module to fully exploit valuable information obtained from concatenating features through channel-wise and spatial-wise relationships. Furthermore, we develop a Channel-Spatial Squeeze-and-Excitation module, a modified network backbone that enhances the representation ability of important channels and correspondences through the squeeze-and-excitation operation. T-Net++ not only preserves the permutation-equivariance manner for correspondence pruning, but also gathers rich contextual information, thereby enhancing the effectiveness of the network. Experimental results demonstrate that T-Net++ outperforms other state-of-the-art correspondence pruning methods on various benchmarks and excels in two extended tasks.

T-Net++:用于双视图对应性剪枝的有效换向-方差网络
我们为双视图对应剪枝任务提出了一个概念新颖、灵活有效的框架(命名为 T-Net++)。T-Net++ 包括两种独特的结构:"-''结构和"|''结构。-''结构利用迭代学习策略来处理对应关系,而"|''结构则整合了"-''结构的所有特征信息,并产生离群器权重。此外,在"|''"结构中,我们设计了一个新的局部-全局注意力融合模块,以充分利用通过通道和空间关系串联特征所获得的有价值信息。此外,我们还开发了 "信道-空间挤压-激发 "模块,这是一种改进的网络骨干,通过挤压-激发操作增强了重要信道和对应关系的表示能力。T-Net++ 不仅保留了用于对应关系剪枝的置换-方差方式,还收集了丰富的上下文信息,从而提高了网络的有效性。实验结果表明,T-Net++ 在各种基准测试中的表现优于其他最先进的对应剪枝方法,并在两项扩展任务中表现出色。我们的代码将发布在 https://github.com/guobaoxiao/T-Net 网站上。
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信