Large-scale phase retrieval

TL;DR

This paper introduces LPR, an efficient large-scale phase retrieval method that extends existing algorithms to complex space, achieving high-fidelity results with low computational cost across various imaging modalities.

Contribution

The work develops a novel large-scale phase retrieval framework combining plug-and-play generalized-alternating-projection with neural networks, enabling ultra-large-scale imaging with improved accuracy and efficiency.

Findings

Outperforms existing algorithms with up to 17dB SNR improvement.

Achieves over tenfold increase in computational efficiency.

Demonstrates 8K phase retrieval in minutes.

Abstract

High-throughput computational imaging requires efficient processing algorithms to retrieve multi-dimensional and multi-scale information. In computational phase imaging, phase retrieval (PR) is required to reconstruct both amplitude and phase in complex space from intensity-only measurements. The existing PR algorithms suffer from the tradeoff among low computational complexity, robustness to measurement noise and strong generalization on different modalities. In this work, we report an efficient large-scale phase retrieval technique termed as LPR. It extends the plug-and-play generalized-alternating-projection framework from real space to nonlinear complex space. The alternating projection solver and enhancing neural network are respectively derived to tackle the measurement formation and statistical prior regularization. This framework compensates the shortcomings of each operator, so as to realize high-fidelity phase retrieval with low computational complexity and strong generalization. We applied the technique for a series of computational phase imaging modalities including coherent diffraction imaging, coded diffraction pattern imaging, and Fourier ptychographic microscopy. Extensive simulations and experiments validate that the technique outperforms the existing PR algorithms with as much as 17dB enhancement on signal-to-noise ratio, and more than one order-of-magnitude increased running efficiency. Besides, we for the first time demonstrate ultra-large-scale phase retrieval at the 8K level (7680$\times$4320 pixels) in minute-level time.