@article{Cai2024, 
author = {Jun-Xiong Cai and Tai-Jiang Mu and Yu-Kun Lai},
title = {FilterGNN: Image feature matching with cascaded outlier filters and linear attention},
year = {2024},
journal = {Computational Visual Media},
volume = {10},
number = {5},
pages = {873-884},
keywords = {transformer, sparse reconstruction, visual localization, image matching, linear attention},
url = {https://www.sciopen.com/article/10.1007/s41095-023-0363-3},
doi = {10.1007/s41095-023-0363-3},
abstract = {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.}
}