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

arXiv: https://arxiv.org/abs/2404.01360 · HTML: https://mlsanity.com/paper/2404.01360/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 59 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks](https://mlsanity.com/paper/1901.06523/) (2019)
- [Phase recovery and holographic image reconstruction using deep learning in neural networks](https://mlsanity.com/paper/1705.04286/) (2017)
- [Lensless computational imaging through deep learning](https://mlsanity.com/paper/1702.08516/) (2017)
- [Reliable deep-learning-based phase imaging with uncertainty quantification](https://mlsanity.com/paper/1901.02038/) (2019)
- [AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging](https://mlsanity.com/paper/2109.14053/) (2021)
- [Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization](https://mlsanity.com/paper/2204.10533/) (2022)
- [Real-time coherent diffraction inversion using deep generative networks](https://mlsanity.com/paper/1806.03992/) (2018)
- [Cross-modality deep learning brings bright-field microscopy contrast to holography](https://mlsanity.com/paper/1811.07103/) (2018)
- [Self-supervised learning of hologram reconstruction using physics consistency](https://mlsanity.com/paper/2209.08288/) (2022)
- [Physics Constrained Unsupervised Deep Learning for Rapid, High Resolution Scanning Coherent Diffraction Reconstruction](https://mlsanity.com/paper/2306.11014/) (2023)
- [Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks](https://mlsanity.com/paper/2102.12281/) (2021)
- [eFIN: Enhanced Fourier Imager Network for generalizable autofocusing and pixel super-resolution in holographic imaging](https://mlsanity.com/paper/2301.03162/) (2023)
- [Phase retrieval for Fourier Ptychography under varying amount of measurements](https://mlsanity.com/paper/1805.03593/) (2018)
- [Neural Architecture Search generated Phase Retrieval Net for Real-time Off-axis Quantitative Phase Imaging](https://mlsanity.com/paper/2210.14231/) (2022)
- [Physics-driven universal twin-image removal network for digital in-line holographic microscopy](https://mlsanity.com/paper/2308.04471/) (2023)

## Built on by (most cited first, 1 of 1)

- [PiLocNet: Physics-informed neural network on 3D localization with rotating point spread function](https://mlsanity.com/paper/2410.13295/) (2024)

## Abstract (arXiv)

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.