Year: 2021
Type: preprint
Abstract: The plug-and-play priors (PnP) and regularization by denoising (RED) methods have become widely used for solving inverse problems by leveraging pre-trained deep denoisers as image priors. While the empirical imaging performance and the theoretical convergence properties of these algorithms have been widely investigated, their recovery properties have not previously been theoretically analyzed. We address this gap by showing how to establish theoretical recovery guarantees for PnP/RED by assuming that the solution of these methods lies near the fixed-points of a deep neural network. We also present numerical results comparing the recovery performance of PnP/RED in compressive sensing against that of recent compressive sensing algorithms based on generative models. Our numerical results suggest that PnP with a pre-trained artifact removal network provides significantly better results compared to the existing state-of-the-art methods.
Source: arXiv (Cornell University)
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Awards: CAREER: Reconciling Model-Based and Learning-Based Imaging: Theory, Algorithms, and Applications, CIF: Small: Collaborative Research: Signal Processing for Nonlinear Diffractive Imaging: Acquisition, Reconstruction, and Applications, CAREER: Optimized Sensing and Recovery for Computational Imaging, G802336593
OpenAlex ID: W3171539944