CVOct 7, 2025

Compact Multi-level-prior Tensor Representation for Hyperspectral Image Super-resolution

arXiv:2510.06098v1h-index: 46
Originality Incremental advance
AI Analysis

This work addresses a domain-specific problem in remote sensing and image processing, offering an incremental improvement over existing tensor-based methods by better handling multi-level priors.

The paper tackles hyperspectral image super-resolution by fusing hyperspectral and multispectral images, proposing a compact tensor model that effectively incorporates multi-level priors and achieves improved performance on multiple datasets.

Fusing a hyperspectral image with a multispectral image acquired over the same scene, \textit{i.e.}, hyperspectral image super-resolution, has become a popular computational way to access the latent high-spatial-spectral-resolution image. To date, a variety of fusion methods have been proposed, among which the tensor-based ones have testified that multiple priors, such as multidimensional low-rankness and spatial total variation at multiple levels, effectively drive the fusion process. However, existing tensor-based models can only effectively leverage one or two priors at one or two levels, since simultaneously incorporating multi-level priors inevitably increases model complexity. This introduces challenges in both balancing the weights of different priors and optimizing multi-block structures. Concerning this, we present a novel hyperspectral super-resolution model compactly characterizing these multi-level priors of hyperspectral images within the tensor framework. Firstly, the proposed model decouples the spectral low-rankness and spatial priors by casting the latent high-spatial-spectral-resolution image into spectral subspace and spatial maps via block term decomposition. Secondly, these spatial maps are stacked as the spatial tensor encoding the high-order spatial low-rankness and smoothness priors, which are co-modeled via the proposed non-convex mode-shuffled tensor correlated total variation. Finally, we draw inspiration from the linearized alternating direction method of multipliers to design an efficient algorithm to optimize the resulting model, theoretically proving its Karush-Kuhn-Tucker convergence under mild conditions. Experiments on multiple datasets demonstrate the effectiveness of the proposed algorithm. The code implementation will be available from https://github.com/WongYinJ.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes