Adaptive Expert Learning for Hyperspectral and Multispectral Image Fusion

Hyperspectral image (HSI) and multispectral image (MSI) fusion aims to generate high-resolution HSI by leveraging the high spectral fidelity of HSI and the fine spatial details of MSI. However, most existing methods rely on static fusion strategies that assume global consistency in modality contributions, ignoring the inherent regional variability in real-world remote sensing scenes. To address this limitation, we propose an adaptive expert learning framework (AELF) that dynamically models the modal dominance of different regions and adaptively adjusts fusion strategies accordingly. A core component of AELF is the modality-guided complementary module (MGCM), which establishes bidirectional cross-attention pathways between HSI and MSI. It enables each modality to adaptively discover complementary cues across multiple scales while suppressing irrelevant information, providing enhanced feature representation for subsequent fine-grained fusion. Building upon this, we designed the attribute-aware mixture of fusion experts (AMoFE) module, which decomposes the fused features into spectral, spatial, and edge subspaces. Each component is modeled by a specialized expert network, with a soft routing mechanism dynamically adjusting expert contributions based on contextual cues. Extensive experiments on benchmark datasets and a real-world dataset demonstrate that AELF achieves state-of-the-art performance in terms of spectral fidelity and spatial sharpness. Furthermore, our results confirm that the improved data quality brought by the proposed method effectively enhances the overall performance of downstream tasks. The code will be available at https://github.com/Hewq77/AELF.