Learning Degradation-Aware Deep Prior for Hyperspectral Image Reconstruction

Reconstructing the 3-D hyperspectral image (HSI) from 2-D snapshot measurements is a key task in spectral snapshot compressive imaging (SCI). Traditional model-based HSI reconstruction methods rely on hand-crafted priors. Recently, deep unfolding networks (DUNs) learn the priors using convolutional neural networks (CNNs) and have achieved satisfactory results. Most of the DUNs assume the degradations of SCI are known. However, due to the phase aberration and distortion problems in a real imaging process, there is a certain gap between the ideal and real degradation patterns, which may hinder the accurate HSI reconstruction. In this study, we propose a degradation-aware deep prior learning network (D2PL-Net), which tries to adaptively learn the practical degradation matrix during HSI reconstruction, and thus bridges the gap between the ideal and real degradations. Specifically, we first propose a joint variational compressive reconstruction model, and both the latent HSI and unknown degradation can be explicitly solved. By unfolding the solutions into a deep network, D2PL-Net is built, which mainly consists of two parts, degradation matrix learning (DML) mechanism and degradation-guided spectral–spatial transformer (DSST) in each stage. The former learns the degradation that approximates the real one; the latter represents the deep prior of latent HSI, and it could exploit the spectralwise and spatialwise long-range dependencies of HSI under the guidance of learned degradation, and then reconstruct the HSI. To ensure an effective training of D2PL-Net, we propose a joint loss function constraining the HSI reconstruction errors, degradation fidelity and degradation consistency. Experiments on simulated and real-life datasets show that the proposed method is competitive with the state-of-the-art methods.