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. Our paper is also available at: https: // arxiv. org/ abs/ 2211. 00799 .
Original language | English (US) |
---|---|
Article number | 153 |
Journal | IS and T International Symposium on Electronic Imaging Science and Technology |
Volume | 35 |
Issue number | 14 |
DOIs | |
State | Published - 2023 |
Event | IS and T International Symposium on Electronic Imaging: 21st Computational Imaging, COIMG 2023 - San Francisco, United States Duration: Jan 15 2023 → Jan 19 2023 |
Bibliographical note
Publisher Copyright:© 2023, Society for Imaging Science and Technology.