PhaseGAN: a deep-learning phase-retrieval approach for unpaired datasets.

@article{Zhang2021PhaseGANAD,
  title={PhaseGAN: a deep-learning phase-retrieval approach for unpaired datasets.},
  author={Yuhe Zhang and Mike Andreas Noack and Patrik Vagovi{\vc} and Kamel Fezzaa and Francisco M. Garc{\'i}a-Moreno and Tobias Ritschel and Pablo Villanueva-Perez},
  journal={Optics express},
  year={2021},
  volume={29 13},
  pages={
          19593-19604
        }
}
Phase retrieval approaches based on deep learning (DL) provide a framework to obtain phase information from an intensity hologram or diffraction pattern in a robust manner and in real-time. However, current DL architectures applied to the phase problem rely on i) paired datasets, i. e., they are only applicable when a satisfactory solution of the phase problem has been found, and ii) the fact that most of them ignore the physics of the imaging process. Here, we present PhaseGAN, a new DL… 

Figures and Tables from this paper

Investigating the robustness of a learning-based method for quantitative phase retrieval from propagation-based x-ray phase contrast measurements under laboratory conditions

Objective. Quantitative phase retrieval (QPR) in propagation-based x-ray phase contrast imaging of heterogeneous and structurally complicated objects is challenging under laboratory conditions due to

Practical Phase Retrieval Using Double Deep Image Priors

As a single-instance method, this work identifies the connection between the difficulty level and the number and variety of symmetries in PR problems, and proposes a novel method using double deep image priors.

Towards Practical Single-shot Phase Retrieval with Physics-Driven Deep Neural Network

A novel physics-driven multi-scale DNN structure dubbed PPRNet, which is much faster and more accurate than the traditional physicsdriven PR approaches and has a feedforward structure and can be end-to-end trained.

ContransGAN: Convolutional Neural Network Coupling Global Swin-Transformer Network for High-Resolution Quantitative Phase Imaging with Unpaired Data

Optical quantitative phase imaging (QPI) is a frequently used technique to recover biological cells with high contrast in biology and life science for cell detection and analysis. However, the

Nonlinear primal dual-method phase retrieval for X-ray in-line phase contrast imaging

The in-line X-ray phase contrast imaging technique relies on the measurement of Fresnel diffraction intensity patterns due to the phase shift and the absorption induced by the object. The recovery of

DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging using Digital Holography

A new DL architecture based on generative adversarial networks that uses a discriminative network for realizing a semantic measure for reconstruction quality while using a generative network as a function approximator to model the inverse of hologram formation is proposed.

SiPRNet: End-to-End Learning for Single-Shot Phase Retrieval

A novel deep neural network structure named SiSPRNet for phase retrieval based on a single Fourier intensity measurement is designed and demonstrated that the proposed approach consistently outperforms other deep learning methods in single-shot maskless phase retrieval.

Analysis of Deep Learning-Based Phase Retrieval Algorithm Performance for Quantitative Phase Imaging Microscopy

Quantitative phase imaging has been of interest to the science and engineering community and has been applied in multiple research fields and applications. Recently, the data-driven approach of

Performance Evaluation of Deep Neural Network Model for Coherent X-ray Imaging

The investigation shows that the deep neural network model is robust to a limited dynamic range and partially coherent X-ray illumination in comparison to the traditional phase retrieval, although it is more sensitive to the noise than the iteration-based method.

References

SHOWING 1-10 OF 58 REFERENCES

Real-time coherent diffraction inversion using deep generative networks

This work demonstrates the training and testing of CDI NN, a pair of deep deconvolutional networks trained to predict structure and phase in real space of a 2D object from its corresponding far-field diffraction intensities alone, opening the door to real-time imaging.

eHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstruction.

The eHoloNet is proposed, which can reconstruct the object wavefront directly from a single-shot in-line digital hologram and has strong robustness to the change of optical path difference between reference beam and object light and does not require the reference beam to be a plane or spherical wave.

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.

Phase recovery and holographic image reconstruction using deep learning in neural networks

It is demonstrated that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate training, and this deep learning-based approach provides an entirely new framework to conduct holographic imaging by rapidly eliminating twin-image and self-interference-related spatial artifacts.

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

This work presents an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples, and introduces a cycle consistency loss to push F(G(X)) ≈ X (and vice versa).

Image-to-Image Translation with Conditional Adversarial Networks

Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Lensless computational imaging through deep learning

It is demonstrated for the first time to the knowledge that deep neural networks can be trained to solve end-to-end inverse problems in computational imaging.

The Perception-Distortion Tradeoff

It is proved mathematically that distortion and perceptual quality are at odds with each other, and generative-adversarial-nets (GANs) provide a principled way to approach the perception-distortion bound.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a
...