TAR: Text Semantic Assisted Cross-modal Image Registration Framework for Optical and SAR Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Zhuoyu, Quan, Dou, Huyan, Ning, He, Pei, Wang, Shuang, Jiao, Licheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918497012940800
author Cai, Zhuoyu
Quan, Dou
Huyan, Ning
He, Pei
Wang, Shuang
Jiao, Licheng
author_facet Cai, Zhuoyu
Quan, Dou
Huyan, Ning
He, Pei
Wang, Shuang
Jiao, Licheng
contents Existing deep learning-based methods can capture shared features from optical and synthetic aperture radar (SAR) images for spatial alignment. However, optical-SAR registration remains challenging under large geometric deformations, because the model needs to simultaneously handle cross-modal appearance discrepancies and complex spatial transformations. To address this issue, this paper proposes a text semantic-assisted cross-modal image registration framework, named TAR, for optical and SAR images. TAR exploits text semantic priors from remote sensing scenes and land-cover categories to alleviate the modality gap and enhance cross-modal feature learning. TAR consists of three components: a multi-scale visual feature learning (MSFL) module, a text-assisted feature enhancement (TAFE) module, and a coarse-to-fine dense matching (CFDM) module. MSFL extracts multi-scale visual features from optical and SAR images. TAFE constructs text descriptors related to remote sensing scenes and land-cover objects, and uses a frozen RemoteCLIP text encoder to extract text features. These text features are introduced through visual-text interaction to enhance high-level visual features for more reliable coarse matching. CFDM then establishes coarse correspondences based on the enhanced high-level features and refines the matched locations using low-level features. Experimental results on cross-modal remote sensing images demonstrate the effectiveness of TAR, which achieves stronger matching performance than several state-of-the-art methods and yields significant gains under large geometric deformations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12064
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TAR: Text Semantic Assisted Cross-modal Image Registration Framework for Optical and SAR Images
Cai, Zhuoyu
Quan, Dou
Huyan, Ning
He, Pei
Wang, Shuang
Jiao, Licheng
Computer Vision and Pattern Recognition
Existing deep learning-based methods can capture shared features from optical and synthetic aperture radar (SAR) images for spatial alignment. However, optical-SAR registration remains challenging under large geometric deformations, because the model needs to simultaneously handle cross-modal appearance discrepancies and complex spatial transformations. To address this issue, this paper proposes a text semantic-assisted cross-modal image registration framework, named TAR, for optical and SAR images. TAR exploits text semantic priors from remote sensing scenes and land-cover categories to alleviate the modality gap and enhance cross-modal feature learning. TAR consists of three components: a multi-scale visual feature learning (MSFL) module, a text-assisted feature enhancement (TAFE) module, and a coarse-to-fine dense matching (CFDM) module. MSFL extracts multi-scale visual features from optical and SAR images. TAFE constructs text descriptors related to remote sensing scenes and land-cover objects, and uses a frozen RemoteCLIP text encoder to extract text features. These text features are introduced through visual-text interaction to enhance high-level visual features for more reliable coarse matching. CFDM then establishes coarse correspondences based on the enhanced high-level features and refines the matched locations using low-level features. Experimental results on cross-modal remote sensing images demonstrate the effectiveness of TAR, which achieves stronger matching performance than several state-of-the-art methods and yields significant gains under large geometric deformations.
title TAR: Text Semantic Assisted Cross-modal Image Registration Framework for Optical and SAR Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12064