A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 47; no. 6; pp. 4684 - 4698
• Main Authors: Wang, Yinjian, Li, Wei, Gui, Yuanyuan, Du, Qian, Fowler, James E.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2025
• Subjects: Anisotropic; Degradation; Hyperspectral imaging; hyperspectral super-resolution; Image fusion; Mathematical models; Matrix decomposition; nonconvex surrogate; Optimization; recoverability; sparse coding; Spatial resolution; Superresolution; tensor factorization; Tensors; Vectors
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2025.3545605

Hyperspectral super-resolution is commonly accomplished by the fusing of a hyperspectral imaging of low spatial resolution with a multispectral image of high spatial resolution, and many tensor-based approaches to this task have been recently proposed. Yet, it is assumed in such tensor-based methods that the spatial-blurring operation that creates the observed hyperspectral image from the desired super-resolved image is separable into independent horizontal and vertical blurring. Recent work has argued that such separable spatial degradation is ill-equipped to model the operation of real sensors which may exhibit, for example, anisotropic blurring. To accommodate this fact, a generalized tensor formulation based on a Kronecker decomposition is proposed to handle any general spatial-degradation matrix, including those that are not separable as previously assumed. Analysis of the generalized formulation reveals conditions under which exact recovery of the desired super-resolved image is guaranteed, and a practical algorithm for such recovery, driven by a blockwise-group-sparsity regularization, is proposed. Extensive experimental results demonstrate that the proposed generalized tensor approach outperforms not only traditional matrix-based techniques but also state-of-the-art tensor-based methods; the gains with respect to the latter are especially significant in cases of anisotropic spatial blurring.