Decoupled Data Consistency with Diffusion Purification for Image Restoration
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_ | 1866909641835806720 |
|---|---|
| author | Li, Xiang Kwon, Soo Min Liang, Shijun Alkhouri, Ismail R. Ravishankar, Saiprasad Qu, Qing |
| author_facet | Li, Xiang Kwon, Soo Min Liang, Shijun Alkhouri, Ismail R. Ravishankar, Saiprasad Qu, Qing |
| contents | Diffusion models have recently gained traction as a powerful class of deep generative priors, excelling in a wide range of image restoration tasks due to their exceptional ability to model data distributions. To solve image restoration problems, many existing techniques achieve data consistency by incorporating additional likelihood gradient steps into the reverse sampling process of diffusion models. However, the additional gradient steps pose a challenge for real-world practical applications as they incur a large computational overhead, thereby increasing inference time. They also present additional difficulties when using accelerated diffusion model samplers, as the number of data consistency steps is limited by the number of reverse sampling steps. In this work, we propose a novel diffusion-based image restoration solver that addresses these issues by decoupling the reverse process from the data consistency steps. Our method involves alternating between a reconstruction phase to maintain data consistency and a refinement phase that enforces the prior via diffusion purification. Our approach demonstrates versatility, making it highly adaptable for efficient problem-solving in latent space. Additionally, it reduces the necessity for numerous sampling steps through the integration of consistency models. The efficacy of our approach is validated through comprehensive experiments across various image restoration tasks, including image denoising, deblurring, inpainting, and super-resolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06054 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Decoupled Data Consistency with Diffusion Purification for Image Restoration Li, Xiang Kwon, Soo Min Liang, Shijun Alkhouri, Ismail R. Ravishankar, Saiprasad Qu, Qing Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Signal Processing Diffusion models have recently gained traction as a powerful class of deep generative priors, excelling in a wide range of image restoration tasks due to their exceptional ability to model data distributions. To solve image restoration problems, many existing techniques achieve data consistency by incorporating additional likelihood gradient steps into the reverse sampling process of diffusion models. However, the additional gradient steps pose a challenge for real-world practical applications as they incur a large computational overhead, thereby increasing inference time. They also present additional difficulties when using accelerated diffusion model samplers, as the number of data consistency steps is limited by the number of reverse sampling steps. In this work, we propose a novel diffusion-based image restoration solver that addresses these issues by decoupling the reverse process from the data consistency steps. Our method involves alternating between a reconstruction phase to maintain data consistency and a refinement phase that enforces the prior via diffusion purification. Our approach demonstrates versatility, making it highly adaptable for efficient problem-solving in latent space. Additionally, it reduces the necessity for numerous sampling steps through the integration of consistency models. The efficacy of our approach is validated through comprehensive experiments across various image restoration tasks, including image denoising, deblurring, inpainting, and super-resolution. |
| title | Decoupled Data Consistency with Diffusion Purification for Image Restoration |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2403.06054 |