Residual Degradation Learning Unfolding Framework with Mixing Priors across Spectral and Spatial for Compressive Spectral Imaging
This work addresses a core problem in coded aperture snapshot spectral imaging for applications like remote sensing or medical imaging, but it appears incremental as it builds on deep unfolding methods with specific improvements.
The paper tackles the problem of recovering 3D spectral cubes from 2D measurements in compressive spectral imaging by proposing a residual degradation learning unfolding framework and a MixS^2 Transformer to address sensing matrix mismatches and enhance spectral-spatial priors, achieving superior performance over existing methods.
To acquire a snapshot spectral image, coded aperture snapshot spectral imaging (CASSI) is proposed. A core problem of the CASSI system is to recover the reliable and fine underlying 3D spectral cube from the 2D measurement. By alternately solving a data subproblem and a prior subproblem, deep unfolding methods achieve good performance. However, in the data subproblem, the used sensing matrix is ill-suited for the real degradation process due to the device errors caused by phase aberration, distortion; in the prior subproblem, it is important to design a suitable model to jointly exploit both spatial and spectral priors. In this paper, we propose a Residual Degradation Learning Unfolding Framework (RDLUF), which bridges the gap between the sensing matrix and the degradation process. Moreover, a Mix$S^2$ Transformer is designed via mixing priors across spectral and spatial to strengthen the spectral-spatial representation capability. Finally, plugging the Mix$S^2$ Transformer into the RDLUF leads to an end-to-end trainable neural network RDLUF-Mix$S^2$. Experimental results establish the superior performance of the proposed method over existing ones.