{"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":"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 \n<inline-formula><tex-math>$\\hbox{``}-$</tex-math></inline-formula>\n'' structure and the \n<inline-formula><tex-math>$\\hbox{``}|$</tex-math></inline-formula>\n'' structure. The \n<inline-formula><tex-math>$\\hbox{``}-$</tex-math></inline-formula>\n'' structure utilizes an iterative learning strategy to process correspondences, while the \n<inline-formula><tex-math>$\\hbox{``}|$</tex-math></inline-formula>\n'' structure integrates all feature information of the \n<inline-formula><tex-math>$\\hbox{``}-$</tex-math></inline-formula>\n'' structure and produces inlier weights. Moreover, within the \n<inline-formula><tex-math>$\\hbox{``}|$</tex-math></inline-formula>\n'' 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.","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":"46 12","pages":"10629-10644"},"PeriodicalIF":0.0000,"publicationDate":"2024-08-16","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://ieeexplore.ieee.org/document/10637773/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","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
$\hbox{``}-$
'' structure and the
$\hbox{``}|$
'' structure. The
$\hbox{``}-$
'' structure utilizes an iterative learning strategy to process correspondences, while the
$\hbox{``}|$
'' structure integrates all feature information of the
$\hbox{``}-$
'' structure and produces inlier weights. Moreover, within the
$\hbox{``}|$
'' 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.