Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging
Zongliang Wu, Ruiying Lu, Ying Fu, Xin Yuan

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: ) the ill-posed problem of dealing with heavily degraded measurement, and ) 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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSparse and Compressive Sensing Techniques · Image and Signal Denoising Methods · Photoacoustic and Ultrasonic Imaging
MethodsDiffusion · Latent Diffusion Model
