Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging

TL;DR

This paper introduces a novel approach combining latent diffusion models with deep unfolding for snapshot spectral compressive imaging, significantly improving reconstruction quality and efficiency by generating degradation-free priors.

Contribution

It proposes integrating a lightweight latent diffusion model to enhance deep unfolding methods, addressing ill-posed problems and detail recovery in spectral imaging reconstruction.

Findings

Outperforms existing methods in reconstruction quality

Reduces computational cost with a lightweight diffusion model

Demonstrates superior results on synthetic and real datasets

Abstract

Snapshot compressive spectral imaging reconstruction aims to reconstruct three-dimensional spatial-spectral images from a single-shot two-dimensional compressed measurement. Existing state-of-the-art methods are mostly based on deep unfolding structures but have intrinsic performance bottlenecks: $i$) the ill-posed problem of dealing with heavily degraded measurement, and $ii$) the regression loss-based reconstruction models being prone to recover images with few details. In this paper, we introduce a generative model, namely the latent diffusion model (LDM), to generate degradation-free prior to enhance the regression-based deep unfolding method. Furthermore, to overcome the large computational cost challenge in LDM, we propose a lightweight model to generate knowledge priors in deep unfolding denoiser, and integrate these priors to guide the reconstruction process for compensating high-quality spectral signal details. Numeric and visual comparisons on synthetic and real-world datasets illustrate the superiority of our proposed method in both reconstruction quality and computational efficiency. Code will be released.