Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Hanwen, Karpur, Arjun, Cao, Bingyi, Huang, Qixing, Araujo, Andre
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.12979
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916254766333952
author Jiang, Hanwen
Karpur, Arjun
Cao, Bingyi
Huang, Qixing
Araujo, Andre
author_facet Jiang, Hanwen
Karpur, Arjun
Cao, Bingyi
Huang, Qixing
Araujo, Andre
contents The image matching field has been witnessing a continuous emergence of novel learnable feature matching techniques, with ever-improving performance on conventional benchmarks. However, our investigation shows that despite these gains, their potential for real-world applications is restricted by their limited generalization capabilities to novel image domains. In this paper, we introduce OmniGlue, the first learnable image matcher that is designed with generalization as a core principle. OmniGlue leverages broad knowledge from a vision foundation model to guide the feature matching process, boosting generalization to domains not seen at training time. Additionally, we propose a novel keypoint position-guided attention mechanism which disentangles spatial and appearance information, leading to enhanced matching descriptors. We perform comprehensive experiments on a suite of $7$ datasets with varied image domains, including scene-level, object-centric and aerial images. OmniGlue's novel components lead to relative gains on unseen domains of $20.9\%$ with respect to a directly comparable reference model, while also outperforming the recent LightGlue method by $9.5\%$ relatively.Code and model can be found at https://hwjiang1510.github.io/OmniGlue
format Preprint
id arxiv_https___arxiv_org_abs_2405_12979
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
Jiang, Hanwen
Karpur, Arjun
Cao, Bingyi
Huang, Qixing
Araujo, Andre
Computer Vision and Pattern Recognition
The image matching field has been witnessing a continuous emergence of novel learnable feature matching techniques, with ever-improving performance on conventional benchmarks. However, our investigation shows that despite these gains, their potential for real-world applications is restricted by their limited generalization capabilities to novel image domains. In this paper, we introduce OmniGlue, the first learnable image matcher that is designed with generalization as a core principle. OmniGlue leverages broad knowledge from a vision foundation model to guide the feature matching process, boosting generalization to domains not seen at training time. Additionally, we propose a novel keypoint position-guided attention mechanism which disentangles spatial and appearance information, leading to enhanced matching descriptors. We perform comprehensive experiments on a suite of $7$ datasets with varied image domains, including scene-level, object-centric and aerial images. OmniGlue's novel components lead to relative gains on unseen domains of $20.9\%$ with respect to a directly comparable reference model, while also outperforming the recent LightGlue method by $9.5\%$ relatively.Code and model can be found at https://hwjiang1510.github.io/OmniGlue
title OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.12979