Deep learning phase recovery: data-driven, physics-driven, or combining both?

Abstract

Phase recovery, calculating the phase of a light wave from its intensity measurements, is essential for various applications, such as coherent diffraction imaging, adaptive optics, and biomedical imaging. It enables the reconstruction of an object's refractive index distribution or topography as well as the correction of imaging system aberrations. In recent years, deep learning has been proven to be highly effective in addressing phase recovery problems. Two most direct deep learning phase recovery strategies are data-driven (DD) with supervised learning mode and physics-driven (PD) with self-supervised learning mode. DD and PD achieve the same goal in different ways and lack the necessary study to reveal similarities and differences. Therefore, in this paper, we comprehensively compare these two deep learning phase recovery strategies in terms of time consumption, accuracy, generalization ability, ill-posedness adaptability, and prior capacity. What's more, we propose a co-driven (CD) strategy of combining datasets and physics for the balance of high- and low-frequency information. The codes for DD, PD, and CD are publicly available at https://github.com/kqwang/DLPR.

arXiv comment24 pages, 13 figures

References in corpus (12)

• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• Deep learning approach to Fourier ptychographic microscopy
• On the use of deep learning for phase recovery
• Reliable deep-learning-based phase imaging with uncertainty quantification
• Cross-modality deep learning brings bright-field microscopy contrast to holography
• Real-time coherent diffraction inversion using deep generative networks
• Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization
• Self-supervised learning of hologram reconstruction using physics consistency
• Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks
• Physics-driven universal twin-image removal network for digital in-line holographic microscopy
• eFIN: Enhanced Fourier Imager Network for generalizable autofocusing and pixel super-resolution in holographic imaging

Cited by in corpus (1)

• PiLocNet: Physics-informed neural network on 3D localization with rotating point spread function