Robust Fusion Controller: Degradation-aware Image Fusion with Fine-grained Language Instructions
This work addresses the challenge of reliable image fusion in adverse environments for applications like surveillance or autonomous systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of image fusion in real-world environments with diverse and spatially varying degradations by proposing a robust fusion controller that uses fine-grained language instructions to achieve degradation-aware fusion, demonstrating robustness against various composite degradations, especially in challenging flare scenarios.
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.