Prior for Multi-Task Inverse Problems in Image Reconstruction Using Deep Equilibrium Models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Prior for Multi-Task Inverse Problems in Image Reconstruction Using Deep Equilibrium Models

Résumé

Inverse problems in imaging consider the reconstruction of clean images from degraded observations, like deblurring or inpainting. These inverse problems are generally ill-posed. Solving them therefore requires regularization, which exists in multiple approaches: plug-and-play (pnp) methods are designed to generically solve any inverse problem by replacing a regularizing proximal operator with a denoiser. Unrolled methods perform a fixed number of iterations and train a network endto-end for a specific degradation, but necessitate retraining for each specific degradation. Deep equilibrium models (DEQs), on the other hand, iterate an unrolled method until convergence and thereby enable end-to-end training on the reconstruction error with simplified back-propagation. We have investigated to what extent a solution for several inverse problems can be found by employing a multi-task DEQ. This MT-DEQ is used to train a prior on the actual estimation error, in contrast to a theoretical noise model used for pnp methods. This has the advantage that the resulting prior is trained for a range of degradations beyond pure Gaussian denoising. The investigation also demonstrates that different search methods can be used in training (forward-backward) and in testing (alternating direction method of multipliers).
Fichier principal
Vignette du fichier
MTDEQ_CR_submittedtoEUSIPCO.pdf (2.24 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04195526 , version 1 (04-09-2023)
hal-04195526 , version 2 (20-10-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04195526 , version 2

Citer

Samuel Willingham, Mårten Sjöström, Christine Guillemot. Prior for Multi-Task Inverse Problems in Image Reconstruction Using Deep Equilibrium Models. EUSIPCO 2023 - 31st European Signal Processing Conference, Sep 2023, Helsinki (Aalto University School of Economics), Finland. pp.1-5. ⟨hal-04195526v2⟩
44 Consultations
96 Téléchargements

Partager

Gmail Facebook X LinkedIn More