Unsupervised Multimodal UAV Image Registration via Style Transfer and Cascade Network
Remote Sensing · 24.06.2025 · 17 (13) · 2160
DOI: 10.3390/rs17132160 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.06.2025. Verfasst von Xiaoye Bi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Young Scientists Fund of the National Natural Science Foundation of China, Shaanxi Key Research and Development Program.
Abstract (Originalsprache)
Cross-modal image registration for unmanned aerial vehicle (UAV) platforms presents significant challenges due to large-scale deformations, distinct imaging mechanisms, and pronounced modality discrepancies. This paper proposes a novel multi-scale cascaded registration network based on style transfer that achieves superior performance: up to 67% reduction in mean squared error (from 0.0106 to 0.0068), 9.27% enhancement in normalized cross-correlation, 26% improvement in local normalized cross-correlation, and 8% increase in mutual information compared to state-of-the-art methods. The architecture integrates a cross-modal style transfer network (CSTNet) that transforms visible images into pseudo-infrared representations to unify modality characteristics, and a multi-scale cascaded registration network (MCRNet) that performs progressive spatial alignment across multiple resolution scales using diffeomorphic deformation modeling to ensure smooth and invertible transformations. A self-supervised learning paradigm based on image reconstruction eliminates reliance on manually annotated data while maintaining registration accuracy through synthetic deformation generation. Extensive experiments on the LLVIP dataset demonstrate the method’s robustness under challenging conditions involving large-scale transformations, with ablation studies confirming that style transfer contributes 28% MSE improvement and diffeomorphic registration prevents 10.6% performance degradation. The proposed approach provides a robust solution for cross-modal image registration in dynamic UAV environments, offering significant implications for downstream applications such as target detection, tracking, and surveillance.
Förderung
- Young Scientists Fund of the National Natural Science Foundation of China
- Shaanxi Key Research and Development Program
Zitieren
APA
Bi, X., Qie, R., Tao, C., Zhang, Z., & Xu, Y. (2025). Unsupervised Multimodal UAV Image Registration via Style Transfer and Cascade Network. Remote Sensing, 17(13), 2160. https://doi.org/10.3390/rs17132160
Vancouver
Bi X, Qie R, Tao C, Zhang Z, Xu Y. Unsupervised Multimodal UAV Image Registration via Style Transfer and Cascade Network. Remote Sensing. 2025;17(13):2160. doi:10.3390/rs17132160
BibTeX
@article{Bi2025,
author = {Bi, Xiaoye and Qie, Rongkai and Tao, Chengyang and Zhang, Zhaoxiang and Xu, Yuelei},
title = {Unsupervised Multimodal UAV Image Registration via Style Transfer and Cascade Network},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {13},
pages = {2160},
doi = {10.3390/rs17132160}
}
EUVIMED