DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model

This paper endeavors to advance the precision of snap-shot compressive imaging (SCI) reconstruction for multi-spectral image (MSI). To achieve this, we integrate the ad-vantageous attributes of established SCI techniques and an image generative model, propose a novel structured zero-shot diffusion model, dubbed DiffSCI. DiffSCI leverages the structural insights from the deep prior and optimization-based methodologies, complemented by the generative ca-pabilities offered by the contemporary denoising diffusion model. Specifically, firstly, we employ a pre-trained diffusion model, which has been trained on a substantial corpus of RGB images, as the generative denoiser within the Plug-and-Play framework for the first time. This integration allows for the successful completion of SCI reconstruction, especially in the case that current methods struggle to address effectively. Secondly, we systematically account for spectral band correlations and introduce a robust methodology to mitigate wavelength mismatch, thus enabling seamless adaptation of the RGB diffusion model to MSIs. Thirdly, an accelerated algorithm is implemented to expedite the resolution of the data subproblem. This augmentation not only accelerates the convergence rate but also elevates the quality of the reconstruction process. We present extensive testing to show that DiffSCI exhibits discernible performance en-hancements over prevailing self-supervised and zero-shot approaches, surpassing even supervised transformer coun-terparts across both simulated and real datasets. Code is at https://github.com/PAN083/DiffSCI.