FilterGNN: Image feature matching with cascaded outlier filters and linear attention

Cai, Jun-Xiong, Mu, Tai-Jiang and Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 2024. FilterGNN: Image feature matching with cascaded outlier filters and linear attention. Computational Visual Media 10 (5) , pp. 873-884. 10.1007/s41095-023-0363-3

PDF - Published Version Download (8MB)

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.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Additional Information:	License information from Publisher: LICENSE 1: URL: http://creativecommons.org/licenses/by/4.0/, Type: open-access
Publisher:	SpringerOpen
ISSN:	2096-0433
Date of First Compliant Deposit:	24 October 2024
Date of Acceptance:	23 June 2023
Last Modified:	24 Oct 2024 10:45
URI:	https://orca.cardiff.ac.uk/id/eprint/173298

Actions (repository staff only)

Edit Item