Wei Wei

TL;DR: This paper first conducts clustering in the spatial domain of the input conventional image and adopts the intra-cluster self-expressiveness model to implicitly depict the clustering manifold structure, which enables learning the complicated manifold structure via solving a constrained ridge regression model without knowing the exact form of the manifold.

TL;DR: This work develops a two-stage SR network that leverages two consecutive modules: a fusion module and an adaptation module, to recover the latent HSI in a coarse-to-fine scheme and introduces a simple degeneration network to assist learning both the adaptation module and the degeneration in an unsupervised way.

TL;DR: A novel single HSI super-resolution method is presented, termed Grouped Deep Recursive Residual Network (GDRRN), which learns to directly map an input low resolution HSI to a high resolution H SI with a specialized deep neural network.

TL;DR: A novel cluster sparsity field based HSI reconstruction framework which explicitly models both the intrinsic correlation between measurements within the spectrum for a particular pixel, and the similarity between pixels due to the spatial structure of the HSI, thus combating the effects of noise corruption or undersampling.

TL;DR: In this paper, a set of alignment matrices is introduced to align the tensor representations from both domains into the invariant tensor subspace, which can be learned adaptively from the data using the proposed alternative minimization scheme.