The inherent difficulty in acquiring accurately co-registered RGB-hyperspectral image (HSI) pairs has significantly impeded the practical deployment of current data-driven Hyperspectral Image Generation (HIG) networks in engineering applications. Gleichzeitig, the ill-posed nature of the aligning constraints, compounded with the complexities of mining cross-domain features, also hinders the advancement of unpaired HIG (UnHIG) tasks. In this paper, we conquer these challenges by modeling the UnHIG to range space interaction and compensations of null space through Range-Null Space Decomposition (RND) methodology. Specifically, the introduced contrastive learning effectively aligns the geometric and spectral distributions of unpaired data by building the interaction of range space, considering the consistent feature in degradation process. Following this, we map the frequency representations of dual-domain input and thoroughly mining the null space, like degraded and high-frequency components, through the proposed Non-uniform Kolmogorov-Arnold Networks. Extensive comparative experiments demonstrate that it establishes a new benchmark in UnHIG.

翻译：准确配准的RGB-高光谱图像（HSI）对在获取上的固有困难，严重阻碍了当前数据驱动的高光谱图像生成（HIG）网络在工程应用中的实际部署。同时，对齐约束本身的不适定性，加上挖掘跨域特征的复杂性，也阻碍了非配对HIG（UnHIG）任务的发展。在本文中，我们通过将UnHIG建模为值域空间的交互与零空间的补偿，并采用值域-零空间分解（RND）方法，来克服这些挑战。具体而言，考虑到退化过程中的一致性特征，所引入的对比学习通过构建值域空间的交互，有效对齐了非配对数据的几何与光谱分布。随后，我们映射双域输入的频率表示，并通过提出的非均匀Kolmogorov-Arnold网络，充分挖掘零空间（如退化与高频分量）。广泛的对比实验表明，该方法在UnHIG领域确立了新的性能基准。