Işıl Çağatay, Oktem Figen S, Koç Aykut
Appl Opt. 2019 Jul 10;58(20):5422-5431. doi: 10.1364/AO.58.005422.
The classical phase retrieval problem is the recovery of a constrained image from the magnitude of its Fourier transform. Although there are several well-known phase retrieval algorithms, including the hybrid input-output (HIO) method, the reconstruction performance is generally sensitive to initialization and measurement noise. Recently, deep neural networks (DNNs) have been shown to provide state-of-the-art performance in solving several inverse problems such as denoising, deconvolution, and superresolution. In this work, we develop a phase retrieval algorithm that utilizes two DNNs together with the model-based HIO method. First, a DNN is trained to remove the HIO artifacts, and is used iteratively with the HIO method to improve the reconstructions. After this iterative phase, a second DNN is trained to remove the remaining artifacts. Numerical results demonstrate the effectiveness of our approach, which has little additional computational cost compared to the HIO method. Our approach not only achieves state-of-the-art reconstruction performance but also is more robust to different initialization and noise levels.
经典的相位恢复问题是从其傅里叶变换的幅度中恢复一个受约束的图像。尽管有几种著名的相位恢复算法，包括混合输入输出（HIO）方法，但重建性能通常对初始化和测量噪声很敏感。最近，深度神经网络（DNN）已被证明在解决诸如去噪、反卷积和超分辨率等几个逆问题方面提供了最先进的性能。在这项工作中，我们开发了一种相位恢复算法，该算法将两个DNN与基于模型的HIO方法一起使用。首先，训练一个DNN来去除HIO伪影，并与HIO方法迭代使用以改进重建。在这个迭代阶段之后，训练第二个DNN来去除剩余的伪影。数值结果证明了我们方法的有效性，与HIO方法相比，该方法几乎没有额外的计算成本。我们的方法不仅实现了最先进的重建性能，而且对不同的初始化和噪声水平更具鲁棒性。
