| Autor: |
Fermanian, Rita, Le Pendu, Mikael, Guillemot, Christine |
| Předmět: |
|
| Zdroj: |
SIAM Journal on Imaging Sciences; 2023, Vol. 16 Issue 2, p585-613, 29p |
| Abstrakt: |
The plug-and-play framework makes it possible to integrate advanced image denoising priors into optimization algorithms to efficiently solve a variety of image restoration tasks generally formulated as maximum a posteriori (MAP) estimation problems. The plug-and-play alternating direction method of multipliers (ADMM) and the regularization by denoising (RED) algorithms are two examples of such methods that made a breakthrough in image restoration. However, the former plug-and-play approach only applies to proximal algorithms. And while the explicit regularization in RED can be used in various algorithms, including gradient descent, the gradient of the regularizer computed as a denoising residual leads to several approximations of the underlying image prior in the MAP interpretation of the denoiser. We show that it is possible to train a network directly modeling the gradient of a MAP regularizer while jointly training the corresponding MAP denoiser. We use this network in gradient-based optimization methods and obtain better results compared to other generic plug-and-play approaches. We also show that the regularizer can be used as a pretrained network for unrolled gradient descent. Lastly, we show that the resulting denoiser allows for a better convergence of the plug-and-play ADMM. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
