Phase recovery, calculating the phase of a light wave from its intensity measurements, is essential for various applications, such as coherent diffraction imaging, adaptive optics, and biomedical imaging. It enables the reconstruction of an object's refractive index distribution or topography as well as the correction of imaging system aberrations. In recent years, deep learning has been proven to be highly effective in addressing phase recovery problems. Two main deep learning phase recovery strategies are data-driven (DD) with supervised learning mode and physics-driven (PD) with self-supervised learning mode. DD and PD achieve the same goal in different ways and lack the necessary study to reveal similarities and differences. Therefore, in this paper, we comprehensively compare these two deep learning phase recovery strategies in terms of time consumption, accuracy, generalization ability, ill-posedness adaptability, and prior capacity. What's more, we propose a co-driven (CD) strategy of combining datasets and physics for the balance of high- and low-frequency information. The codes for DD, PD, and CD are publicly available at https://github.com/kqwang/DLPR.

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.

Yair Rivenson and Aydogan Ozcan Electrical & Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA Bioengineering Department, University of California, Los Angeles, CA, 90095, USA California NanoSystems Institute, University of California, Los Angeles, CA, 90095, USA http://innovate.ee.ucla.edu/welcome.html Abstract: We discuss recently emerging applications of the state-of-art deep learning methods on optical microscopy and microscopic image reconstruction, which enable new transformations among different modes and modalities of microscopic imaging, driven entirely by image data. We believe that deep learning will fundamentally change both the hardware and image reconstruction methods used in optical microscopy in a holistic manner. Recent results in applications of deep learning [1] have proven to be transformative for various fields, redefining the state of the art results achieved by earlier machine learning techniques. As an example, one of the fields that has significantly benefited from the ongoing deep learning revolution is machine vision, with landmark results that enable new capabilities in autonomous cars, fault analysis, security applications, as well as entertainment.

Deep learning has been experiencing a true renaissance especially over the last decade, and it uses multi-layered artificial neural networks for automated analysis of data. Deep learning is one of the most exciting forms of machine learning that is behind several recent leapfrog advances in technology including for example real-time speech recognition and translation as well image/video labeling and captioning, among many others. Especially in image analysis, deep learning shows significant promise for automated search and labeling of features of interest, such as abnormal regions in a medical image. Now, UCLA researchers have demonstrated a new use for deep learning – this time to reconstruct a hologram and form a microscopic image of an object. In a recent article that is published in Light: Science & Applications, a journal of the Springer Nature, UCLA researchers have demonstrated that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate training.

Deep learning has been experiencing a true renaissance especially over the last decade, and it uses multi-layered artificial neural networks for automated analysis of data. Deep learning is one of the most exciting forms of machine learning that is behind several recent leapfrog advances in technology including for example real-time speech recognition and translation as well image/video labeling and captioning, among many others. Especially in image analysis, deep learning shows significant promise for automated search and labeling of features of interest, such as abnormal regions in a medical image. Now, UCLA researchers have demonstrated a new use for deep learning – this time to reconstruct a hologram and form a microscopic image of an object. In a recent article that is published in Light: Science & Applications, a journal of the Springer Nature, UCLA researchers have demonstrated that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate training.