HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xiaolong, Yu, Lei, Zhang, Yingying, Lao, Jiangwei, Ru, Lixiang, Zhong, Liheng, Chen, Jingdong, Zhang, Yu, Yang, Ming
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913575637876736
author Wang, Xiaolong
Yu, Lei
Zhang, Yingying
Lao, Jiangwei
Ru, Lixiang
Zhong, Liheng
Chen, Jingdong
Zhang, Yu
Yang, Ming
author_facet Wang, Xiaolong
Yu, Lei
Zhang, Yingying
Lao, Jiangwei
Ru, Lixiang
Zhong, Liheng
Chen, Jingdong
Zhang, Yu
Yang, Ming
contents Feature matching between image pairs is a fundamental problem in computer vision that drives many applications, such as SLAM. Recently, semi-dense matching approaches have achieved substantial performance enhancements and established a widely-accepted coarse-to-fine paradigm. However, the majority of existing methods focus on improving coarse feature representation rather than the fine-matching module. Prior fine-matching techniques, which rely on point-to-patch matching probability expectation or direct regression, often lack precision and do not guarantee the continuity of feature points across sequential images. To address this limitation, this paper concentrates on enhancing the fine-matching module in the semi-dense matching framework. We employ a lightweight and efficient homography estimation network to generate the perspective mapping between patches obtained from coarse matching. This patch-to-patch approach achieves the overall alignment of two patches, resulting in a higher sub-pixel accuracy by incorporating additional constraints. By leveraging the homography estimation between patches, we can achieve a dense matching result with low computational cost. Extensive experiments demonstrate that our method achieves higher accuracy compared to previous semi-dense matchers. Meanwhile, our dense matching results exhibit similar end-point-error accuracy compared to previous dense matchers while maintaining semi-dense efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06700
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation
Wang, Xiaolong
Yu, Lei
Zhang, Yingying
Lao, Jiangwei
Ru, Lixiang
Zhong, Liheng
Chen, Jingdong
Zhang, Yu
Yang, Ming
Computer Vision and Pattern Recognition
Feature matching between image pairs is a fundamental problem in computer vision that drives many applications, such as SLAM. Recently, semi-dense matching approaches have achieved substantial performance enhancements and established a widely-accepted coarse-to-fine paradigm. However, the majority of existing methods focus on improving coarse feature representation rather than the fine-matching module. Prior fine-matching techniques, which rely on point-to-patch matching probability expectation or direct regression, often lack precision and do not guarantee the continuity of feature points across sequential images. To address this limitation, this paper concentrates on enhancing the fine-matching module in the semi-dense matching framework. We employ a lightweight and efficient homography estimation network to generate the perspective mapping between patches obtained from coarse matching. This patch-to-patch approach achieves the overall alignment of two patches, resulting in a higher sub-pixel accuracy by incorporating additional constraints. By leveraging the homography estimation between patches, we can achieve a dense matching result with low computational cost. Extensive experiments demonstrate that our method achieves higher accuracy compared to previous semi-dense matchers. Meanwhile, our dense matching results exhibit similar end-point-error accuracy compared to previous dense matchers while maintaining semi-dense efficiency.
title HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.06700