Hyperspectral Image Super-Resolution Using Differentiation and Cross-Domain Feature

The rich spectral information in hyperspectral images (HSIs) require effective joint extraction of spectral and spatial features for super-resolution (SR) tasks. To better capture spectral–spatial representations and restore edge textures, we propose the differentiation and cross-domain feature extraction network (DCDFENet) for HSI SR. Its core module enhances reconstruction by leveraging cross-domain interactions and differential features. Differentiation and cross-domain feature extraction (DCDFE) consists of three components: cross-domain and multiscale feature extraction (CDMSFE), which uses separated 3-D convolutions and cross-domain connections to extract complementary features at multiple scales; spectral feature differentiation highlighting attention (SFDHA), which emphasizes significant spectral variations via differentiation and attention mechanisms; and edge feature extraction (EFE), which integrates Laplacian filtering and an extreme value feature extraction (EVFE) to enhance spatial edge textures. In addition, a loss function based on singular value decomposition (SVD) further mitigates spectral distortion. Experiments on three benchmark datasets demonstrate that our method achieves superior performance on peak signal-to-noise ratio (PSNR), mean PSNR (MPSNR), structural similarity (SSIM), and spectral angle mapping (SAM) metrics.