An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
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_ | 1866929404651765760 |
|---|---|
| author | Bai, Weimin Wang, Yifei Chen, Wenzheng Sun, He |
| author_facet | Bai, Weimin Wang, Yifei Chen, Wenzheng Sun, He |
| contents | Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce. In this paper, we propose EMDiffusion, an expectation-maximization (EM) approach to train diffusion models from corrupted observations. Our method alternates between reconstructing clean images from corrupted data using a known diffusion model (E-step) and refining diffusion model weights based on these reconstructions (M-step). This iterative process leads the learned diffusion model to gradually converge to the true clean data distribution. We validate our method through extensive experiments on diverse computational imaging tasks, including random inpainting, denoising, and deblurring, achieving new state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01014 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations Bai, Weimin Wang, Yifei Chen, Wenzheng Sun, He Computer Vision and Pattern Recognition Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce. In this paper, we propose EMDiffusion, an expectation-maximization (EM) approach to train diffusion models from corrupted observations. Our method alternates between reconstructing clean images from corrupted data using a known diffusion model (E-step) and refining diffusion model weights based on these reconstructions (M-step). This iterative process leads the learned diffusion model to gradually converge to the true clean data distribution. We validate our method through extensive experiments on diverse computational imaging tasks, including random inpainting, denoising, and deblurring, achieving new state-of-the-art performance. |
| title | An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.01014 |