HPGC-Diff: Hybrid-Prior Guided Coupled Diffusion for Unsupervised Hyperspectral Image Super-Resolution

Fusing a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) is a widely adopted strategy for hyperspectral image super-resolution (HISR), for which diffusion models have recently shown strong potential. However, existing methods still suffer from two critical limitations: 1) spectral models based on MLPs lack the necessary inductive bias for sequential data, structurally disregarding the local correlations between adjacent spectral bands; 2) spatial models struggle to simultaneously leverage the specific structures from the observed image with the generic priors learned from large-scale datasets. To overcome these challenges, we propose a Hybrid-Prior Guided Coupled Diffusion (HPGC-Diff) for the unsupervised HISR task, which effectively integrates low-rank prior, spectral local correlation prior, and generic prior. Leveraging the low-rank representation, we decompose the target HR-HSI into two low-dimensional components and establish separate processes for their joint reconstruction. Specifically, we design a 1D U-Net spectral diffusion model that effectively learns the structured spectral distribution from the LR-HSI. For spatial modeling, we introduce a dual-source spatial model that integrates generic prior from multiple pre-trained diffusion models to provide a powerful generative capability, with conditional feature extracted from the HR-MSI by a dedicated network to inject fine-grained structural details. Finally, spatial and spectral diffusion sampling is jointly guided and alternated with conditional feature optimization to ensure stable convergence under observational constraints. Extensive experiments on simulated and real-world datasets demonstrate that HPGC-Diff achieves superior performance compared to state-of-the-art methods.