EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DecoupledFM: Decoupling Invariant and Specific Representations for Robust Cross-Modal Feature Matching

Chunhu Zhang, Zujian Liu, Yizhuo Zhang, Hai Yang, Kun Sun

Remote Sensing · 10.11.2026 · 18 (22) · 3872

DOI: 10.3390/rs18223872 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.11.2026. Verfasst von Chunhu Zhang und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deep Earth Probe and Mineral Resources Exploration - National Science and Technology Major Project of China, China Geological Survey, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-modal image matching, such as between optical-SAR or RGB-infrared images, remains a critical yet challenging task due to severe, non-linear radiometric distortions that plague existing end-to-end matchers. We identify feature entanglement as a potential cause of this performance degradation: standard backbones implicitly couple modality-invariant geometric structures with modality-specific appearances. This coupling, while effective within a single domain, breaks down under drastic domain shifts, leading to matching failure. To address this, we propose DecoupledFM, a semi-dense matching framework that uses separate invariant and specific feature branches. The core of our method is the Invariance-Guided Disentanglement Module (IGDM), which enforces a trio of synergistic constraints—feature cyclic substitution for modality invariance, reconstruction with an orthogonality loss for disentanglement completeness, and keypoint score prediction for geometric saliency awareness—to achieve a principled decomposition. This novel design effectively injects the structural priors of sparse descriptors into a high-precision semi-dense architecture. During inference, only the disentangled invariant features are used for robust coarse matching via an Efficient Cross-View Matching Module, while fine refinement also uses backbone features. Extensive experiments on 20 challenging subsets demonstrate that DecoupledFM achieves state-of-the-art performance, significantly outperforming existing methods.

Förderung

  • Deep Earth Probe and Mineral Resources Exploration - National Science and Technology Major Project of China
  • China Geological Survey
  • National Natural Science Foundation of China
  • Hubei Provincial Natural Science Foundation of China

Zitieren

APA

Zhang, C., Liu, Z., Zhang, Y., Yang, H., & Sun, K. (2026). DecoupledFM: Decoupling Invariant and Specific Representations for Robust Cross-Modal Feature Matching. Remote Sensing, 18(22), 3872. https://doi.org/10.3390/rs18223872

Vancouver

Zhang C, Liu Z, Zhang Y, Yang H, Sun K. DecoupledFM: Decoupling Invariant and Specific Representations for Robust Cross-Modal Feature Matching. Remote Sensing. 2026;18(22):3872. doi:10.3390/rs18223872

BibTeX
@article{Zhang2026,
  author = {Zhang, Chunhu and Liu, Zujian and Zhang, Yizhuo and Yang, Hai and Sun, Kun},
  title = {DecoupledFM: Decoupling Invariant and Specific Representations for Robust Cross-Modal Feature Matching},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {3872},
  doi = {10.3390/rs18223872}
}
Kostenlos starten →