On the use of deep learning for phase recovery

Abstract

Phase recovery (PR) refers to calculating the phase of the light field from its intensity measurements. As exemplified from quantitative phase imaging and coherent diffraction imaging to adaptive optics, PR is essential for reconstructing the refractive index distribution or topography of an object and correcting the aberration of an imaging system. In recent years, deep learning (DL), often implemented through deep neural networks, has provided unprecedented support for computational imaging, leading to more efficient solutions for various PR problems. In this review, we first briefly introduce conventional methods for PR. Then, we review how DL provides support for PR from the following three stages, namely, pre-processing, in-processing, and post-processing. We also review how DL is used in phase image processing. Finally, we summarize the work in DL for PR and outlook on how to better use DL to improve the reliability and efficiency in PR. Furthermore, we present a live-updating resource (https://github.com/kqwang/phase-recovery) for readers to learn more about PR.

82 pages, 32 figures

References in corpus (24)

• Wide-field, high-resolution Fourier ptychographic microscopy
• Photonics for artificial intelligence and neuromorphic computing
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Deep Learning Microscopy
• Solution to the twin image problem in holography
• Reliable deep-learning-based phase imaging with uncertainty quantification
• Phase Retrieval: From Computational Imaging to Machine Learning
• Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization
• Self-supervised learning of hologram reconstruction using physics consistency
• Diffractive all-optical computing for quantitative phase imaging
• Resolution-enhanced parallel coded ptychography for high-throughput optical imaging
• To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects
• Real-time stain-free classification of cancer cells and blood cells using interferometric phase microscopy and machine learning
• Rapid and stain-free quantification of viral plaque via lens-free holography and deep learning
• Deep learning-based color holographic microscopy
• Blood-coated sensor for high-throughput ptychographic cytometry on a Blu-ray disc
• On the interplay between physical and content priors in deep learning for computational imaging
• SiSPRNet: End-to-End Learning for Single-Shot Phase Retrieval
• eFIN: Enhanced Fourier Imager Network for generalizable autofocusing and pixel super-resolution in holographic imaging
• GRB 101225A as Orphan Dipole Radiation of a Newborn Magnetar with Precession Rotation in an Off-Axis Gamma-Ray Burst
• Unfolded Algorithms for Deep Phase Retrieval
• Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging
• ADMM based Fourier phase retrieval with untrained generative prior
• Optimizing Intermediate Representations of Generative Models for Phase Retrieval

Cited by in corpus (12)

• All-optical complex field imaging using diffractive processors
• Deep learning phase recovery: data-driven, physics-driven, or combining both?
• Res-U2Net: Untrained Deep Learning for Phase Retrieval and Image Reconstruction
• A generative approach for lensless imaging in low-light conditions
• Neuromorphic Shack-Hartmann wave normal sensing
• Phase retrieval via Zernike phase contrast microscopy with an untrained neural network
• Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram
• Quantum process tomography of structured optical gates with convolutional neural networks
• Machine-learning-enabled characterization of individual ring resonators in integrated photonic lattices
• Neural Architecture Search generated Phase Retrieval Net for Real-time Off-axis Quantitative Phase Imaging
• Single Snapshot Distillation for Phase Coded Mask Design in Phase Retrieval
• Focal-plane wavefront sensing with moderately broadband light using a short multi-mode fiber