Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors. Inspired by recent advancements in deep generative models, we propose an HSI Super-resolution (SR) approach with Conditional Diffusion Models (HSR-Diff) that merges a high-resolution (HR) multispectral image (MSI) with the corresponding LR-HSI. HSR-Diff generates an HR-HSI via repeated refinement, in which the HR-HSI is initialized with pure Gaussian noise and iteratively refined. At each iteration, the noise is removed with a Conditional Denoising Transformer (CDF ormer) that is trained on denoising at different noise levels, conditioned on the hierarchical feature maps of HR-MSI and LR-HSI. In addition, a progressive learning strategy is employed to exploit the global information of full-resolution images. Systematic experiments have been conducted on four public datasets, demonstrating that HSR-Diff outperforms state-of-the-art methods.

翻译：尽管高光谱图像（HSI）在多种计算机视觉任务中展现出显著价值，但其潜力受到由多种物理因素导致的空间域低分辨率（LR）特性的不利影响。受深度生成模型最新进展的启发，我们提出一种基于条件扩散模型的高光谱图像超分辨率（SR）方法（HSR-Diff），该方法将高分辨率（HR）多光谱图像（MSI）与对应的低分辨率高光谱图像（LR-HSI）相融合。HSR-Diff通过反复细化生成高分辨率高光谱图像（HR-HSI），其中HR-HSI初始化为纯高斯噪声并逐步迭代精炼。在每次迭代中，噪声通过条件去噪Transformer（CDFormer）被移除，该Transformer在不同噪声水平下的去噪任务上训练，并以高分辨率多光谱图像与低分辨率高光谱图像的分层特征图为条件。此外，采用渐进式学习策略以充分利用全分辨率图像的全局信息。在四个公开数据集上的系统实验表明，HSR-Diff的性能超越了当前最先进的方法。