Practical phase retrieval using double deep image priors

Z Zhuang, D Yang, F Hofmann, D Barmherzig… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Unsupervised deep learning for phase retrieval via teacher-student distillation

Y Quan, Z Chen, T Pang, H Ji - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Phase retrieval (PR) is a challenging nonlinear inverse problem in scientific imaging that
involves reconstructing the phase of a signal from its intensity measurements. Recently …

Learning conditional generative models for phase retrieval

T Uelwer, S Konietzny, A Oberstrass… - Journal of Machine …, 2023 - jmlr.org
Reconstructing images from magnitude measurements is an important and difficult problem
arising in many research areas, such as X-ray crystallography, astronomical imaging and …

Low-light phase retrieval with implicit generative priors

R Manekar, E Negrini, M Pham… - … on Image Processing, 2024 - ieeexplore.ieee.org
Phase retrieval (PR) is fundamentally important in scientific imaging and is crucial for
nanoscale techniques like coherent diffractive imaging (CDI). Low radiation dose imaging is …

Learning-based lens wavefront aberration recovery

L Chen, Y Hu, J Nie, T Xue, J Gu - Optics Express, 2024 - opg.optica.org
Wavefront aberration describes the deviation of a wavefront in an imaging system from a
desired perfect shape, such as a plane or a sphere, which may be caused by a variety of …

Unlocking inverse problems using deep learning: Breaking symmetries in phase retrieval

K Tayal, CH Lai, R Manekar, Z Zhuang… - … 2020 Workshop on …, 2020 - openreview.net
In many physical systems, inputs related by intrinsic system symmetries generate the same
output. So when inverting such systems, an input is mapped to multiple symmetry-related …

Compressive phase retrieval: Optimal sample complexity with deep generative priors

P Hand, O Leong, V Voroninski - Communications on Pure and …, 2024 - Wiley Online Library
Advances in compressive sensing (CS) provided reconstruction algorithms of sparse signals
from linear measurements with optimal sample complexity, but natural extensions of this …

LoDIP: Low light phase retrieval with deep image prior

R Manekar, E Negrini, M Pham, D Jacobs… - arXiv preprint arXiv …, 2024 - arxiv.org
Phase retrieval (PR) is a fundamental challenge in scientific imaging, enabling nanoscale
techniques like coherent diffractive imaging (CDI). Imaging at low radiation doses becomes …

Optimizing intermediate representations of generative models for phase retrieval

T Uelwer, S Konietzny, S Harmeling - arXiv preprint arXiv:2205.15617, 2022 - arxiv.org
Phase retrieval is the problem of reconstructing images from magnitude-only measurements.
In many real-world applications the problem is underdetermined. When training data is …

Phase retrieval using single-instance deep generative prior

K Tayal, R Manekar, Z Zhuang, D Yang… - Optics and Photonics …, 2021 - opg.optica.org
Phase Retrieval using Single-Instance Deep Generative Prior Page 1 Phase Retrieval using
Single-Instance Deep Generative Prior Kshitij Tayal*1 Raunak Manekar1 Zhong Zhuang 2 …