English

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.

Keywords

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}
}
R2 v1 2026-06-28T04:58:26.674Z