The phase retrieval problem, usually known as reconstructing an estimate of phase object from its diffraction intensity patterns, exists widely in the optical imaging field. In this paper, a deep convolutional neural network (CNN) framework is developed to accomplish the phase reconstruction given a single-shot Fourier measurement, without the requirement of prior knowledge (like nonnegativity and support constraints) or time-consuming iterations. A receptive field and input enhance learning-based design principle is applied to establish the neural network architecture. And a new loss function that combines the structural similarity (SSIM) index and the mean square error (MSE) is taken to further improve the network training. Quantitative (the average SSIM and relative MSE are ~ 0.9900 and 0.0012, respectively) and qualitative (SSIM, ranging from 0.87 to 0.95) phase reconstructions are achieved in the numerical simulation and experiment, respectively. Once the proposed network is well trained, it is convenient for the users to perform the phase reconstruction at a remarkably fast speed (~ 0.425 s). Moreover, our network is considerably robust to different noises and could be trained to additionally function as a denoiser in the phase retrieval process. In practice, the proposed method is able to build an accurate propagation model of the practical imaging system, and significantly enhance and improve the spatial resolution. With the great convenience and high accuracy of phase recovery, the proposed deep CNN framework may be helpful to solve the phase retrieval problem in Fourier imaging systems, like coherent diffraction imaging (CDI), X-ray imaging, and imaging through diffusers, etc.

通常被称为根据其衍射强度图案重建相位对象的估计的相位检索问题在光学成像领域中广泛存在。在本文中，开发了深度卷积神经网络（CNN）框架，以实现单次傅里叶测量的相位重建，而无需先验知识（如非负性和支持约束）或耗时的迭代。接受领域和输入增强基于学习的设计原理被应用于建立神经网络体系结构。结合结构相似度（SSIM）指标和均方误差（MSE）的新损失函数可进一步改善网络训练。定量（平均SSIM和相对MSE分别为〜0.9900和0.0012）和定性（SSIM，数值模拟和实验分别实现了从0.87到0.95的相位重构）。一旦对所提议的网络进行了良好的培训，用户就可以以非常快的速度（约0.425 s）方便地执行相位重建。此外，我们的网络对于不同的噪声具有相当强的鲁棒性，可以训练其在相位检索过程中额外用作降噪器。在实践中，所提出的方法能够建立实际成像系统的精确传播模型，并显着提高和改善空间分辨率。提出的深层CNN框架具有极大的便利性和很高的相位恢复精度，可能有助于解决傅里叶成像系统中的相位恢复问题，例如相干衍射成像（CDI），X射线成像，