Saved in:
Bibliographic Details
Main Authors: Chen, Peiqi, Yu, Lei, Wan, Yi, Pei, Yingying, Liu, Xinyi, Yao, Yongxiang, Zhang, Yingying, Ru, Lixiang, Zhong, Liheng, Chen, Jingdong, Yang, Ming, Zhang, Yongjun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.17312
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916874679222272
author Chen, Peiqi
Yu, Lei
Wan, Yi
Pei, Yingying
Liu, Xinyi
Yao, Yongxiang
Zhang, Yingying
Ru, Lixiang
Zhong, Liheng
Chen, Jingdong
Yang, Ming
Zhang, Yongjun
author_facet Chen, Peiqi
Yu, Lei
Wan, Yi
Pei, Yingying
Liu, Xinyi
Yao, Yongxiang
Zhang, Yingying
Ru, Lixiang
Zhong, Liheng
Chen, Jingdong
Yang, Ming
Zhang, Yongjun
contents Semi-dense feature matching methods have shown strong performance in challenging scenarios. However, the existing pipeline relies on a global search across the entire feature map to establish coarse matches, limiting further improvements in accuracy and efficiency. Motivated by this limitation, we propose a novel pipeline, CasP, which leverages cascaded correspondence priors for guidance. Specifically, the matching stage is decomposed into two progressive phases, bridged by a region-based selective cross-attention mechanism designed to enhance feature discriminability. In the second phase, one-to-one matches are determined by restricting the search range to the one-to-many prior areas identified in the first phase. Additionally, this pipeline benefits from incorporating high-level features, which helps reduce the computational costs of low-level feature extraction. The acceleration gains of CasP increase with higher resolution, and our lite model achieves a speedup of $\sim2.2\times$ at a resolution of 1152 compared to the most efficient method, ELoFTR. Furthermore, extensive experiments demonstrate its superiority in geometric estimation, particularly with impressive cross-domain generalization. These advantages highlight its potential for latency-sensitive and high-robustness applications, such as SLAM and UAV systems. Code is available at https://github.com/pq-chen/CasP.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance
Chen, Peiqi
Yu, Lei
Wan, Yi
Pei, Yingying
Liu, Xinyi
Yao, Yongxiang
Zhang, Yingying
Ru, Lixiang
Zhong, Liheng
Chen, Jingdong
Yang, Ming
Zhang, Yongjun
Computer Vision and Pattern Recognition
Semi-dense feature matching methods have shown strong performance in challenging scenarios. However, the existing pipeline relies on a global search across the entire feature map to establish coarse matches, limiting further improvements in accuracy and efficiency. Motivated by this limitation, we propose a novel pipeline, CasP, which leverages cascaded correspondence priors for guidance. Specifically, the matching stage is decomposed into two progressive phases, bridged by a region-based selective cross-attention mechanism designed to enhance feature discriminability. In the second phase, one-to-one matches are determined by restricting the search range to the one-to-many prior areas identified in the first phase. Additionally, this pipeline benefits from incorporating high-level features, which helps reduce the computational costs of low-level feature extraction. The acceleration gains of CasP increase with higher resolution, and our lite model achieves a speedup of $\sim2.2\times$ at a resolution of 1152 compared to the most efficient method, ELoFTR. Furthermore, extensive experiments demonstrate its superiority in geometric estimation, particularly with impressive cross-domain generalization. These advantages highlight its potential for latency-sensitive and high-robustness applications, such as SLAM and UAV systems. Code is available at https://github.com/pq-chen/CasP.
title CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.17312