Practical Phase Retrieval Using Double Deep Image Priors
Computer Vision and Pattern Recognition
2022-11-03 v1 Machine Learning
Image and Video Processing
Abstract
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.
Cite
@article{arxiv.2211.00799,
title = {Practical Phase Retrieval Using Double Deep Image Priors},
author = {Zhong Zhuang and David Yang and Felix Hofmann and David Barmherzig and Ju Sun},
journal= {arXiv preprint arXiv:2211.00799},
year = {2022}
}