VMatcher: State-Space Semi-Dense Local Feature Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Youssef, Ali
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915419589181440
author Youssef, Ali
author_facet Youssef, Ali
contents This paper introduces VMatcher, a hybrid Mamba-Transformer network for semi-dense feature matching between image pairs. Learning-based feature matching methods, whether detector-based or detector-free, achieve state-of-the-art performance but depend heavily on the Transformer's attention mechanism, which, while effective, incurs high computational costs due to its quadratic complexity. In contrast, Mamba introduces a Selective State-Space Model (SSM) that achieves comparable or superior performance with linear complexity, offering significant efficiency gains. VMatcher leverages a hybrid approach, integrating Mamba's highly efficient long-sequence processing with the Transformer's attention mechanism. Multiple VMatcher configurations are proposed, including hierarchical architectures, demonstrating their effectiveness in setting new benchmarks efficiently while ensuring robustness and practicality for real-time applications where rapid inference is crucial. Source Code is available at: https://github.com/ayoussf/VMatcher
format Preprint
id arxiv_https___arxiv_org_abs_2507_23371
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VMatcher: State-Space Semi-Dense Local Feature Matching
Youssef, Ali
Computer Vision and Pattern Recognition
This paper introduces VMatcher, a hybrid Mamba-Transformer network for semi-dense feature matching between image pairs. Learning-based feature matching methods, whether detector-based or detector-free, achieve state-of-the-art performance but depend heavily on the Transformer's attention mechanism, which, while effective, incurs high computational costs due to its quadratic complexity. In contrast, Mamba introduces a Selective State-Space Model (SSM) that achieves comparable or superior performance with linear complexity, offering significant efficiency gains. VMatcher leverages a hybrid approach, integrating Mamba's highly efficient long-sequence processing with the Transformer's attention mechanism. Multiple VMatcher configurations are proposed, including hierarchical architectures, demonstrating their effectiveness in setting new benchmarks efficiently while ensuring robustness and practicality for real-time applications where rapid inference is crucial. Source Code is available at: https://github.com/ayoussf/VMatcher
title VMatcher: State-Space Semi-Dense Local Feature Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.23371