Double Blind Imaging with Generative Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909555276906496 |
|---|---|
| author | Levac, Brett Jalal, Ajil Ramchandran, Kannan Tamir, Jonathan I. |
| author_facet | Levac, Brett Jalal, Ajil Ramchandran, Kannan Tamir, Jonathan I. |
| contents | Blind inverse problems in imaging arise from uncertainties in the system used to collect (noisy) measurements of images. Recovering clean images from these measurements typically requires identifying the imaging system, either implicitly or explicitly. A common solution leverages generative models as priors for both the images and the imaging system parameters (e.g., a class of point spread functions). To learn these priors in a straightforward manner requires access to a dataset of clean images as well as samples of the imaging system. We propose an AmbientGAN-based generative technique to identify the distribution of parameters in unknown imaging systems, using only unpaired clean images and corrupted measurements. This learned distribution can then be used in model-based recovery algorithms to solve blind inverse problems such as blind deconvolution. We successfully demonstrate our technique for learning Gaussian blur and motion blur priors from noisy measurements and show their utility in solving blind deconvolution with diffusion posterior sampling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21501 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Double Blind Imaging with Generative Modeling Levac, Brett Jalal, Ajil Ramchandran, Kannan Tamir, Jonathan I. Image and Video Processing Computer Vision and Pattern Recognition Blind inverse problems in imaging arise from uncertainties in the system used to collect (noisy) measurements of images. Recovering clean images from these measurements typically requires identifying the imaging system, either implicitly or explicitly. A common solution leverages generative models as priors for both the images and the imaging system parameters (e.g., a class of point spread functions). To learn these priors in a straightforward manner requires access to a dataset of clean images as well as samples of the imaging system. We propose an AmbientGAN-based generative technique to identify the distribution of parameters in unknown imaging systems, using only unpaired clean images and corrupted measurements. This learned distribution can then be used in model-based recovery algorithms to solve blind inverse problems such as blind deconvolution. We successfully demonstrate our technique for learning Gaussian blur and motion blur priors from noisy measurements and show their utility in solving blind deconvolution with diffusion posterior sampling. |
| title | Double Blind Imaging with Generative Modeling |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21501 |