Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging
This work addresses reconstruction challenges in snapshot compressive spectral imaging, an incremental improvement for applications like remote sensing or medical imaging.
The paper tackles the problem of reconstructing 3D spatial-spectral images from 2D compressed measurements in snapshot compressive spectral imaging, addressing bottlenecks like ill-posed degradation and loss of details in existing deep unfolding methods by integrating a latent diffusion model to generate priors, resulting in improved reconstruction quality and computational efficiency as shown in numeric and visual comparisons on synthetic and real-world datasets.
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.