Total Nuclear Norms of Gradients for Hyperspectral Image Pansharpening

Abstract

We introduce a pansharpening method based on a novel regularization function for hyperspectral images (HSI). The regularization is based on the nuclear norms of gradient images. Unlike conventional low-rank priors, we achieve a gradient-based low-rank approximation by minimizing the sum of nuclear-norms associated with rotated planes in the gradient of a HSI. Our method explicitly and simultaneously exploits the correlation in the spectral domain as well as the spatial domain. Our method achieves high-fidelity image pansharpening using a single regularization function without the explicit use of any sparsity-inducing priors such as l0, l1 and TV norms. The proposed regularization is validated on some HSI images with performance comparisons to state-of-the-art methods to demonstrate its superior performance.