Spectral Dynamic Attention Network for Hyperspectral Image Super-Resolution
For researchers in hyperspectral imaging, SDANet provides a more efficient and accurate super-resolution method by addressing spectral redundancy and limited non-linearity in existing deep learning approaches.
SDANet achieves state-of-the-art hyperspectral image super-resolution by adaptively suppressing spectral redundancy and enhancing non-linear modeling, outperforming existing methods on two benchmark datasets.
Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle with substantial spectral redundancy and the limited non-linear modeling capacity of standard feed-forward networks (FFNs). To address these challenges, we propose Spectral Dynamic Attention Network (SDANet), a framework designed to adaptively suppress redundant spectral interactions. SDANet integrates two key components: 1) Dynamic Channel Sparse Attention (DCSA) module that computes channel-wise correlations and selectively preserves the most informative attention responses through dynamic and data-dependent sparsification. 2) Frequency-Enhanced Feed-Forward Network (FE-FFN) that jointly models spatial and frequency-domain representations to enhance non-linear expressiveness. Extensive experiments on two benchmark datasets demonstrate that SDANet achieves state-of-the-art HISR performance while maintaining competitive efficiency. The code will be made publicly available at https://github.com/oucailab/SDANet.