Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916250159939584 |
|---|---|
| author | Chen, Hanyu Hao, Zhixiu Xiao, Liying |
| author_facet | Chen, Hanyu Hao, Zhixiu Xiao, Liying |
| contents | Diffusion models have become a successful approach for solving various image inverse problems by providing a powerful diffusion prior. Many studies tried to combine the measurement into diffusion by score function replacement, matrix decomposition, or optimization algorithms, but it is hard to balance the data consistency and realness. The slow sampling speed is also a main obstacle to its wide application. To address the challenges, we propose Deep Data Consistency (DDC) to update the data consistency step with a deep learning model when solving inverse problems with diffusion models. By analyzing existing methods, the variational bound training objective is used to maximize the conditional posterior and reduce its impact on the diffusion process. In comparison with state-of-the-art methods in linear and non-linear tasks, DDC demonstrates its outstanding performance of both similarity and realness metrics in generating high-quality solutions with only 5 inference steps in 0.77 seconds on average. In addition, the robustness of DDC is well illustrated in the experiments across datasets, with large noise and the capacity to solve multiple tasks in only one pre-trained model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10748 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems Chen, Hanyu Hao, Zhixiu Xiao, Liying Computer Vision and Pattern Recognition Diffusion models have become a successful approach for solving various image inverse problems by providing a powerful diffusion prior. Many studies tried to combine the measurement into diffusion by score function replacement, matrix decomposition, or optimization algorithms, but it is hard to balance the data consistency and realness. The slow sampling speed is also a main obstacle to its wide application. To address the challenges, we propose Deep Data Consistency (DDC) to update the data consistency step with a deep learning model when solving inverse problems with diffusion models. By analyzing existing methods, the variational bound training objective is used to maximize the conditional posterior and reduce its impact on the diffusion process. In comparison with state-of-the-art methods in linear and non-linear tasks, DDC demonstrates its outstanding performance of both similarity and realness metrics in generating high-quality solutions with only 5 inference steps in 0.77 seconds on average. In addition, the robustness of DDC is well illustrated in the experiments across datasets, with large noise and the capacity to solve multiple tasks in only one pre-trained model. |
| title | Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.10748 |