Skip to yearly menu bar Skip to main content


Oral
in
Workshop: Learning-Based Solutions for Inverse Problems

Phase Retrieval via Deep Expectation-Consistent Approximation

Saurav Shastri · Philip Schniter

Keywords: [ Message-Passing Algorithms ] [ generalized linear model ] [ Phase retrieval ] [ Plug-and-Play Algorithms ] [ Expectation-Consistent Approximation ]


Abstract:

The expectation consistent (EC) approximation framework is a state-of-the-art approach for solving (generalized) linear inverse problems with random forward operators and i.i.d. signal priors. In image inverse problems, however, both the forward operator and image pixels are structured, which plagues traditional EC implementations. In this work, we propose a novel incarnation of EC that exploits deep neural networks to handle structured operators and signals. For phase-retrieval, we propose a simplified variant called ''deepECpr'' that reduces to iterative denoising. In experiments recovering natural images from phaseless, shot-noise corrupted, coded-diffraction-pattern outputs, we observe accuracy surpassing the state-of-the-art prDeep (Metzler et al., 2018) and Diffusion Posterior Sampling (Chung et al., 2023) approaches with two-orders-of-magnitude complexity reduction.

Chat is not available.