Several deep learning methods for phase retrieval exist, but most of them fail on realistic data without precise support information. We propose a novel method based on single-instance deep generative prior that works well on complex-valued crystal data.
Cite
@article{arxiv.2106.04812,
title = {Phase Retrieval using Single-Instance Deep Generative Prior},
author = {Kshitij Tayal and Raunak Manekar and Zhong Zhuang and David Yang and Vipin Kumar and Felix Hofmann and Ju Sun},
journal= {arXiv preprint arXiv:2106.04812},
year = {2021}
}