Practical Phase Retrieval Using Double Deep Image Priors

11/02/2022
by   Zhong Zhuang, et al.
0

Phase retrieval (PR) concerns the recovery of complex phases from complex magnitudes. We identify the connection between the difficulty level and the number and variety of symmetries in PR problems. We focus on the most difficult far-field PR (FFPR), and propose a novel method using double deep image priors. In realistic evaluation, our method outperforms all competing methods by large margins. As a single-instance method, our method requires no training data and minimal hyperparameter tuning, and hence enjoys good practicality.

READ FULL TEXT
research
06/09/2021

Phase Retrieval using Single-Instance Deep Generative Prior

Several deep learning methods for phase retrieval exist, but most of the...
research
11/24/2017

PhasePack User Guide

"Phase retrieval" refers to the recovery of signals from the magnitudes ...
research
10/11/2022

Misspecified Phase Retrieval with Generative Priors

In this paper, we study phase retrieval under model misspecification and...
research
03/05/2022

Algebraic theory of phase retrieval

The purpose of this article is to discuss recent advances in the growing...
research
07/07/2022

Pre-training helps Bayesian optimization too

Bayesian optimization (BO) has become a popular strategy for global opti...
research
03/01/2018

prDeep: Robust Phase Retrieval with Flexible Deep Neural Networks

Phase retrieval (PR) algorithms have become an important component in ma...
research
11/26/2021

Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions

Numerous physical systems are described by ordinary or partial different...

Please sign up or login with your details

Forgot password? Click here to reset