Deep Unfolding with Normalizing Flow Priors for Inverse Problems

Many application domains, spanning from computational photography to medical imaging, require recovery of high-fidelity images from noisy, incomplete or partial/compressed measurements. State of the art methods for solving these inverse problems combine deep learning with iterative model-based solve...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-03
Main Authors: Wei, Xinyi, Hans van Gorp, Lizeth Gonzalez Carabarin, Freedman, Daniel, Eldar, Yonina C, Ruud J G van Sloun
Format: Article
Language:English
Subjects:
Algorithms
Inverse problems
Iterative methods
Machine learning
Medical imaging
Recovery
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many application domains, spanning from computational photography to medical imaging, require recovery of high-fidelity images from noisy, incomplete or partial/compressed measurements. State of the art methods for solving these inverse problems combine deep learning with iterative model-based solvers, a concept known as deep algorithm unfolding. By combining a-priori knowledge of the forward measurement model with learned (proximal) mappings based on deep networks, these methods yield solutions that are both physically feasible (data-consistent) and perceptually plausible. However, current proximal mappings only implicitly learn such image priors. In this paper, we propose to make these image priors fully explicit by embedding deep generative models in the form of normalizing flows within the unfolded proximal gradient algorithm. We demonstrate that the proposed method outperforms competitive baselines on various image recovery tasks, spanning from image denoising to inpainting and deblurring.
ISSN:2331-8422
DOI:10.48550/arxiv.2107.02848