Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912278998155264 |
|---|---|
| author | Moroy, Liam Bourmaud, Guillaume Champagnat, Frédéric Giovannelli, Jean-François |
| author_facet | Moroy, Liam Bourmaud, Guillaume Champagnat, Frédéric Giovannelli, Jean-François |
| contents | Plug&Play (PnP) diffusion models are state-of-the-art methods in computed tomography (CT) reconstruction. Such methods usually consider applications where the sinogram contains a sufficient amount of information for the posterior distribution to be concentrated around a single mode, and consequently are evaluated using image-to-image metrics such as PSNR/SSIM. Instead, we are interested in reconstructing compressible flow images from sinograms having a small number of projections, which results in a posterior distribution no longer concentrated or even multimodal. Thus, in this paper, we aim at evaluating the approximate posterior of PnP diffusion models and introduce two posterior evaluation properties. We quantitatively evaluate three PnP diffusion methods on three different datasets for several numbers of projections. We surprisingly find that, for each method, the approximate posterior deviates from the true posterior when the number of projections decreases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21301 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT Moroy, Liam Bourmaud, Guillaume Champagnat, Frédéric Giovannelli, Jean-François Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Plug&Play (PnP) diffusion models are state-of-the-art methods in computed tomography (CT) reconstruction. Such methods usually consider applications where the sinogram contains a sufficient amount of information for the posterior distribution to be concentrated around a single mode, and consequently are evaluated using image-to-image metrics such as PSNR/SSIM. Instead, we are interested in reconstructing compressible flow images from sinograms having a small number of projections, which results in a posterior distribution no longer concentrated or even multimodal. Thus, in this paper, we aim at evaluating the approximate posterior of PnP diffusion models and introduce two posterior evaluation properties. We quantitatively evaluate three PnP diffusion methods on three different datasets for several numbers of projections. We surprisingly find that, for each method, the approximate posterior deviates from the true posterior when the number of projections decreases. |
| title | Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2410.21301 |