Practical Phase Retrieval Using Double Deep Image Priors
This addresses the phase retrieval problem for applications like imaging and signal processing, offering a practical, data-free solution with strong performance gains.
The paper tackled the difficult far-field phase retrieval problem by proposing a novel method using double deep image priors, which outperformed all competing methods by large margins in realistic evaluations.
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.