期刊
OPTICS EXPRESS
卷 30, 期 2, 页码 2247-2264出版社
Optica Publishing Group
DOI: 10.1364/OE.445498
关键词
-
类别
资金
- Southern University of Science and Technology, China [028644-00030]
- Office of Science [DE-SC0021939]
- National Research Foundation Singapore
- U.S. Department of Energy (DOE) [DE-SC0021939] Funding Source: U.S. Department of Energy (DOE)
This study introduces a new method called deep k-learning for reconstructing phase objects from RPI data, which significantly improves results and shows advantages in computational efficiency and robustness against noise.
Randomized probe imaging (RPI) is a single-frame diffractive imaging method that uses highly randomized light to reconstruct the spatial features of a scattering object. The reconstruction process, known as phase retrieval, aims to recover a unique solution for the object without measuring the far-field phase information. Typically, reconstruction is done via time-consuming iterative algorithms. In this work, we propose a fast and efficient deep learning based method to reconstruct phase objects from RPI data. The method, which we call deep k-learning, applies the physical propagation operator to generate an approximation of the object as an input to the neural network. This way, the network no longer needs to parametrize the far-field diffraction physics, dramatically improving the results. Deep k-learning is shown to be computationally efficient and robust to Poisson noise. The advantages provided by our method may enable the analysis of far larger datasets in photon starved conditions, with important applications to the study of dynamic phenomena in physical science and biological engineering. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据