Phase Retrieval Using Double Deep Image Priors
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
Text
Zhuang et al. "Phase Retrieval Using Double Deep Image Priors." NeurIPS 2023 Workshops: Deep_Inverse, 2023.Markdown
[Zhuang et al. "Phase Retrieval Using Double Deep Image Priors." NeurIPS 2023 Workshops: Deep_Inverse, 2023.](https://mlanthology.org/neuripsw/2023/zhuang2023neuripsw-phase/)BibTeX
@inproceedings{zhuang2023neuripsw-phase,
title = {{Phase Retrieval Using Double Deep Image Priors}},
author = {Zhuang, Zhong and Yang, David and Barmherzig, David and Sun, Ju},
booktitle = {NeurIPS 2023 Workshops: Deep_Inverse},
year = {2023},
url = {https://mlanthology.org/neuripsw/2023/zhuang2023neuripsw-phase/}
}