 |
Conference papers
A penalized weighted least squares approach for restoring data corrupted with signal-dependent noise
Abstract : This paper addresses the problem of recovering an image degraded by a linear operator and corrupted with an additive Gaussian noise with a signal-dependent variance. The considered observation model arises in several digital imaging devices. To solve this problem, a variational approach is adopted relying on a weighted least squares criterion which is penalized by a non-smooth function. In this context, the choice of an efficient optimization algorithm remains a challenging task. We propose here to extend a recent primal-dual proximal splitting approach by introducing a preconditioning strategy that is shown to significantly speed up the algorithm convergence. The good performance of the proposed method is illustrated through image restoration examples.
Cited literature [18 references]
https://hal.archives-ouvertes.fr/hal-00733786
Contributor : Emilie Chouzenoux <>
Submitted on : Wednesday, July 3, 2013 - 4:33:11 PM
Last modification on : Wednesday, February 3, 2021 - 7:54:26 AM
Long-term archiving on: : Friday, October 4, 2013 - 2:20:09 AM
Contributor : Emilie Chouzenoux <>
Submitted on : Wednesday, July 3, 2013 - 4:33:11 PM
Last modification on : Wednesday, February 3, 2021 - 7:54:26 AM
Long-term archiving on: : Friday, October 4, 2013 - 2:20:09 AM
File
eusipco2012.pdf
Publisher files allowed on an open archive