Skip to Main content Skip to Navigation
Conference papers

Regularizing the Deep Image Prior with a Learned Denoiser for Linear Inverse Problems

Rita Fermanian 1 Mikael Le Pendu 1 Christine Guillemot 1
1 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : We propose an optimization method coupling a learned denoiser with the untrained generative model, called deep image prior (DIP) in the framework of the Alternating Direction Method of Multipliers (ADMM) method. We also study different regularizers of DIP optimization, for inverse problems in imaging, focusing in particular on denoising and super-resolution. The goal is to make the best of the untrained DIP and of a generic regularizer learned in a supervised manner from a large collection of images. When placed in the ADMM framework, the denoiser is used as a proximal operator and can be learned independently of the considered inverse problem. We show the benefits of the proposed method, in comparison with other regularized DIP methods, for two linear inverse problems, i.e., denoising and super-resolution.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03310533
Contributor : Christine Guillemot <>
Submitted on : Friday, July 30, 2021 - 2:48:49 PM
Last modification on : Wednesday, September 15, 2021 - 3:12:15 AM

File

MMSP-Final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03310533, version 1

Citation

Rita Fermanian, Mikael Le Pendu, Christine Guillemot. Regularizing the Deep Image Prior with a Learned Denoiser for Linear Inverse Problems. MMSP 2021 - IEEE 23rd International Workshop on Multimedia Siganl Processing, Oct 2021, Tampere, Finland. pp.1-6. ⟨hal-03310533⟩

Share

Metrics

Record views

82

Files downloads

167