OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
This addresses the problem of domain generalization in image matching for real-world applications, representing a novel method rather than an incremental improvement.
The paper tackles the limited generalization of learnable image matchers to novel domains by introducing OmniGlue, which leverages vision foundation model guidance and a keypoint position-guided attention mechanism, achieving relative gains of 20.9% on unseen domains compared to a reference model and outperforming LightGlue by 9.5%.
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