ASSR-Net: Anisotropic Structure-Aware and Spectrally Recalibrated Network for Hyperspectral Image Fusion.

Abstract

Hyperspectral image fusion aims to reconstruct high-spatial-resolution hyperspectral images (HR-HSIs) by integrating complementary information from multisource inputs. Despite recent progress, existing methods still face two critical challenges: 1) inadequate reconstruction of anisotropic spatial structures, resulting in blurred details and compromised spatial quality, and 2) spectral distortion during fusion, which hinders fine-grained spectral representation. To address these issues, we propose ASSR-Net: an anisotropic structure-aware and spectrally recalibrated network for hyperspectral image fusion. The ASSR-Net adopts a two-stage fusion strategy comprising anisotropic structure-aware spatial enhancement (ASSE) and hierarchical prior-guided spectral calibration (HPSC). In the first stage, a directional perception fusion module adaptively captures structural features along multiple orientations, effectively reconstructing anisotropic spatial patterns. In the second stage, a spectral recalibration module leverages the original low-resolution hyperspectral image (LR-HSI) as a spectral reference before explicitly correcting spectral deviations in the fused results, thereby enhancing spectral fidelity. Extensive experiments on various benchmark datasets demonstrate that the ASSR-Net consistently outperforms state-of-the-art methods, achieving superior spatial detail preservation and spectral consistency. The code will be available at https://github.com/MSFLabX/ASSRNet.