Large-scale phase retrieval

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 ($$7680\times 4320$$ 7680 × 4320 pixels) in minute-level time.

CNN-Based Cell Analysis: From Image to Quantitative Representation

“…It thus allows phase retrieval at the 4K level (3,840 × 2,748 pixels) in a few seconds. This fast computation time compares well with the recent achievement of a phase retrieval at 8K level (7,680 × 4,320 pixels) in minute-level time [20]. The results of CNNs trained with these fast reconstructions remain in line with the ground truth.…”

Van der Waals two-color infrared photodetector

“…Two-color infrared (IR) technology can identify targets in a complex environment by using the multispectral features of targets, and this technique has been widely used in information technology, life sciences, aerospace, and other fields 1 – 5 . As this technology has been developed, the main research direction has become the integration of two-color detection into single pixels without complex optical components 6 while solving the core problem of separating and detecting dual spectral information independently 7 .…”

Deep learning in optical metrology: a review

“…In the past few years, we have indeed witnessed the rapid progress on high-level artificial intelligence (AI), where deep representations based on convolutional and recurrent neural network models are learned directly from the captured data to solve many tasks in computer vision, computational imaging, and computer-aided diagnosis with unprecedented performance 35 – 37 . The early framework for deep learning was established on artificial neural networks (ANNs) in the 1980s 38 , yet only recently the real impact of deep learning became significant due to the advent of fast graphics processing units (GPUs) and the availability of large datasets 39 .…”