2022/11/02 by Zhong Zhuang, David Yang, Zhuang, Zhong +9 · 4 citations
Computer Science · Engineering · Mathematics · Physics and Astronomy · #Advanced X-ray Imaging Techniques #Algorithm #Artificial intelligence #Bayesian probability #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Connection (principal bundle) #FOS: Computer and information sciences #FOS: Electrical engineering #Field (mathematics) #Focus (optics) #Geometry #Hyperparameter #Image (mathematics) #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Mathematics #Pattern recognition (psychology) #Phase (matter) #Phase retrieval #Physics #Prior probability #Variety (cybernetics) #cs.CV #cs.LG #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2211.00799
published in arXiv (Cornell University) (Cornell University)
arxiv created 2022/11/02 · openalex publication_date 2022/11/02 · arxiv updated 2022/11/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
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.