Practical Phase Retrieval Using Double Deep Image Priors

David Barmherzig; David Yang; Felix Hofmann; Ju Sun; Zhong Zhuang

Practical Phase Retrieval Using Double Deep Image Priors

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.00799 v1 pith:N2U7TPTD submitted 2022-11-02 cs.CV cs.LGeess.IV

Zhong Zhuang , David Yang , Felix Hofmann , David Barmherzig , Ju Sun This is my paper · ORCID

classification cs.CVcs.LGeess.IV

keywords methodcomplexdeepdoubleimagephasepriorsretrieval

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Multilook Coherent Imaging: Theoretical Guarantees and Algorithms
stat.ML 2025-05 conditional novelty 6.0 of 10

Under a deep image prior, the mean squared error of maximum likelihood reconstruction in undersampled multilook coherent imaging is bounded by C1 times n k log n/(m^2 L) plus sqrt(k log n)/m, and a bagged projected gr...

Pith tools