EUVIMEDEUVIMED entdecken
Crossref

Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions

Hao Zhang, Yanping Zha, Qingwei Zhuang, Zhenfeng Shao, Jiayi Ma

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (15) · 12466-12474

DOI: 10.1609/aaai.v40i15.38240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hao Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current image fusion methods struggle to adapt to real-world environments encompassing diverse degradations with spatially varying characteristics. To address this challenge, we propose a robust fusion controller (RFC) capable of achieving degradation-aware image fusion through fine-grained language instructions, ensuring its reliable application in adverse environments. Specifically, RFC first parses language instructions to innovatively derive the functional condition and the spatial condition, where the former specifies the degradation type to remove, while the latter defines its spatial coverage. Then, a composite control priori is generated through a multi-condition coupling network, achieving a seamless transition from abstract language instructions to latent control variables. Subsequently, we design a hybrid attention-based fusion network to aggregate multi-modal information, in which the obtained composite control priori is deeply embedded to linearly modulate the intermediate fused features. To ensure the alignment between language instructions and control outcomes, we introduce a novel language-feature alignment loss, which constrains the consistency between feature-level gains and the composite control priori. Extensive experiments on publicly available datasets demonstrate that our RFC is robust against various composite degradations, particularly in highly challenging flare scenarios.

Zitieren

APA

Zhang, H., Zha, Y., Zhuang, Q., Shao, Z., & Ma, J. (2026). Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions. Proceedings of the AAAI Conference on Artificial Intelligence, 40(15), 12466-12474. https://doi.org/10.1609/aaai.v40i15.38240

Vancouver

Zhang H, Zha Y, Zhuang Q, Shao Z, Ma J. Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(15):12466-12474. doi:10.1609/aaai.v40i15.38240

BibTeX
@article{Zhang2026,
  author = {Zhang, Hao and Zha, Yanping and Zhuang, Qingwei and Shao, Zhenfeng and Ma, Jiayi},
  title = {Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {15},
  pages = {12466--12474},
  doi = {10.1609/aaai.v40i15.38240}
}
Kostenlos starten →