Grid-Reg: Detector-Free Gridized Feature Learning and Matching for Large-Scale SAR-Optical Image Registration
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909767841087488 |
|---|---|
| author | Wei, Xiaochen Guo, Weiwei Zhang, Zenghui Yu, Wenxian |
| author_facet | Wei, Xiaochen Guo, Weiwei Zhang, Zenghui Yu, Wenxian |
| contents | It is highly challenging to register large-scale, heterogeneous SAR and optical images, particularly across platforms, due to significant geometric, radiometric, and temporal differences, which most existing methods struggle to address. To overcome these challenges, we propose Grid-Reg, a grid-based multimodal registration framework comprising a domain-robust descriptor extraction network, Hybrid Siamese Correlation Metric Learning Network (HSCMLNet), and a grid-based solver (Grid-Solver) for transformation parameter estimation. In heterogeneous imagery with large modality gaps and geometric differences, obtaining accurate correspondences is inherently difficult. To robustly measure similarity between gridded patches, HSCMLNet integrates a hybrid Siamese module with a correlation metric learning module (CMLModule) based on equiangular unit basis vectors (EUBVs), together with a manifold consistency loss to promote modality-invariant, discriminative feature learning. The Grid-Solver estimates transformation parameters by minimizing a global grid matching loss through a progressive dual-loop search strategy to reliably find patch correspondences across entire images. Furthermore, we curate a challenging benchmark dataset for SAR-to-optical registration using real-world UAV MiniSAR data and Google Earth optical imagery. Extensive experiments demonstrate that our proposed approach achieves superior performance over state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04233 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Grid-Reg: Detector-Free Gridized Feature Learning and Matching for Large-Scale SAR-Optical Image Registration Wei, Xiaochen Guo, Weiwei Zhang, Zenghui Yu, Wenxian Image and Video Processing Computer Vision and Pattern Recognition It is highly challenging to register large-scale, heterogeneous SAR and optical images, particularly across platforms, due to significant geometric, radiometric, and temporal differences, which most existing methods struggle to address. To overcome these challenges, we propose Grid-Reg, a grid-based multimodal registration framework comprising a domain-robust descriptor extraction network, Hybrid Siamese Correlation Metric Learning Network (HSCMLNet), and a grid-based solver (Grid-Solver) for transformation parameter estimation. In heterogeneous imagery with large modality gaps and geometric differences, obtaining accurate correspondences is inherently difficult. To robustly measure similarity between gridded patches, HSCMLNet integrates a hybrid Siamese module with a correlation metric learning module (CMLModule) based on equiangular unit basis vectors (EUBVs), together with a manifold consistency loss to promote modality-invariant, discriminative feature learning. The Grid-Solver estimates transformation parameters by minimizing a global grid matching loss through a progressive dual-loop search strategy to reliably find patch correspondences across entire images. Furthermore, we curate a challenging benchmark dataset for SAR-to-optical registration using real-world UAV MiniSAR data and Google Earth optical imagery. Extensive experiments demonstrate that our proposed approach achieves superior performance over state-of-the-art methods. |
| title | Grid-Reg: Detector-Free Gridized Feature Learning and Matching for Large-Scale SAR-Optical Image Registration |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.04233 |