FilterGNN:Image feature matching with cascaded outlier filters and linearattention  

作　　者：Jun-Xiong Cai Tai-Jiang Mu Yu-Kun Lai 

机构地区：[1]Key Laboratory of Pervasive Computing,Ministry of Education,Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China [2]School of Computer Science and Informatics,Cardiff University,Wales CF244AG,UK

出　　处：《Computational Visual Media》2024年第5期873-884,共12页计算可视媒体（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant No.62220106003);Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology.

摘　　要：The cross-view matching of local image features is a fundamental task in visual localization and 3D reconstruction.This study proposes FilterGNN,a transformer-based graph neural network(GNN),aiming to improve the matching efficiency and accuracy of visual descriptors.Based on high matching sparseness and coarse-to-fine covisible area detection,FilterGNN utilizes cascaded optimal graph-matching filter modules to dynamically reject outlier matches.Moreover,we successfully adapted linear attention in FilterGNN with post-instance normalization support,which significantly reduces the complexity of complete graph learning from O(N2)to O(N).Experiments show that FilterGNN requires only 6%of the time cost and 33.3%of the memory cost compared with SuperGlue under a large-scale input size and achieves a competitive performance in various tasks,such as pose estimation,visual localization,and sparse 3D reconstruction.

关 键 词：image matching TRANSFORMER linear attention visual localization sparse reconstruction 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]