Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929471981879296 |
|---|---|
| author | Wu, Zongliang Lu, Ruiying Fu, Ying Yuan, Xin |
| author_facet | Wu, Zongliang Lu, Ruiying Fu, Ying Yuan, Xin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_14280 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging Wu, Zongliang Lu, Ruiying Fu, Ying Yuan, Xin Image and Video Processing Computer Vision and Pattern Recognition 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. |
| title | Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.14280 |