Phase retrieval for Fourier Ptychography under varying amount of measurements
Abstract
Fourier Ptychography is a recently proposed imaging technique that yields high-resolution images by computationally transcending the diffraction blur of an optical system. At the crux of this method is the phase retrieval algorithm, which is used for computationally stitching together low-resolution images taken under varying illumination angles of a coherent light source. However, the traditional iterative phase retrieval technique relies heavily on the initialization and also need a good amount of overlap in the Fourier domain for the successively captured low-resolution images, thus increasing the acquisition time and data. We show that an auto-encoder based architecture can be adaptively trained for phase retrieval under both low overlap, where traditional techniques completely fail, and at higher levels of overlap. For the low overlap case we show that a supervised deep learning technique using an autoencoder generator is a good choice for solving the Fourier ptychography problem. And for the high overlap case, we show that optimizing the generator for reducing the forward model error is an appropriate choice. Using simulations for the challenging case of uncorrelated phase an
中文速览
傅里叶叠层成像（Fourier Ptychography）能突破光学系统的分辨率极限，但其核心的相位恢复算法需要在傅里叶域有高度重叠的低分辨率图像，导致拍摄时间长、数据量大，重叠率不足时重建质量急剧下降。作者提出用同一个自编码器（autoencoder）网络框架应对不同重叠率场景：在低重叠率时，以有监督的条件生成对抗网络（cGAN-FP）学习从低分辨率输入到高分辨率强度与相位的映射先验；在高重叠率时，则借鉴"深度图像先验"思路，直接用测量数据驱动网络参数优化（cDIP），让网络结构本身充当隐式正则化项以抑制相位-振幅串扰伪影。在振幅与相位完全不相关这一最具挑战性的仿真场景下，两种方法均优于现有的迭代相位恢复算法，表明深度学习可以在更少采样的条件下实现高质量的相位与强度同步重建，对加速生物医学显微成像和远程遥感成像具有实际意义。
原文 arXiv:1805.03593;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1805.03593v1