Progressive Graph Matching Network for Correspondences

Thumbnail Image
Files
119-120.pdf (6.17 MB)
Date
2023
Authors
Feng, Huihang
Liu, Lupeng
Xiao, Jun
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
This paper presents a progressive graph matching network shorted as PGMNet. The method is more explainable and can match features from easy to hard. PGMNet contains two major blocks: sinkformers module and guided attention module. First, we use sinkformers to get the similar matrix which can be seen as an assignment matrix between two sets of feature keypoints. Matches with highest scores in both rows and columns are selected as pre-matched correspondences. These pre-matched matches can be leveraged to guide the update and matching of ambiguous features. The matching quality can be progressively improved as the the transformer blocks go deeper as visualized in Figure 1. Experiments show that our method achieves better results with typical attention-based methods.
Description

CCS Concepts: Computing methodologies -> Matching; Mixed / augmented reality

        
@inproceedings{
10.2312:pg.20231285
,
booktitle = {
Pacific Graphics Short Papers and Posters
},
editor = {
Chaine, Raphaëlle
 and 
Deng, Zhigang
 and 
Kim, Min H.
},
title = {{
Progressive Graph Matching Network for Correspondences
}},
author = {
Feng, Huihang
 and 
Liu, Lupeng
 and 
Xiao, Jun
},
year = {
2023
},
publisher = {
The Eurographics Association
},
ISBN = {
978-3-03868-234-9
},
DOI = {
10.2312/pg.20231285
}
}
Citation
URI
https://doi.org/10.2312/pg.20231285
 https://diglib.eg.org:443/handle/10.2312/pg20231285
Collections
PG2023 Short Papers and Posters