MFFNet: Multi-domain Feature Fusion Network for Hyperspectral Pansharpening

Hyperspectral (HS) pansharpening is designed to fuse high-spatial resolution panchromatic (PAN) imag-es with low-spatial resolution hyperspectral (LRHS) images to generate high-spatial resolution hyper-spectral (HRHS) images. Because of insufficient consideration of the interference caused by modal dif-ferences in spectral and spatial features during feature fusion, most deep learning–based methods suffer from spectral and spatial distortions in the fusion results. To address these issues, a multidomain feature fusion network (MFFNet) is proposed to perform fine-grained extraction and fusion of multiscale spa-tial–spectral features from PAN and HS images. A dual U-Net model is constructed to extract and fuse multiscale features from PAN and HS images, with spatial-curvature feature enhancement module (SpaFEM) and a spectral-curvature feature enhancement module (SpeFEM) designed to improve curva-ture features. Moreover, a low-rank feature cross-attention module (LFCM) based on matrix factorization is introduced to enhance and complement the PAN and HS image features through cross-modal fusion in a low-dimensional space. Extensive experiments across four datasets are used to demonstrate that the proposed MFFNet outperforms several state-of-the-art methods. The code is available at https://github.com/EchoPhD/MFFNet.