Practical Phase Retrieval Using Double Deep Image Priors

  title={Practical Phase Retrieval Using Double Deep Image Priors},
  author={Zhong Zhuang and David Yang and Felix Hofmann and David A. Barmherzig and Ju Sun},
Phase retrieval (PR) concerns the recovery of complex phases from complex magnitudes. We identify the connection between the difficulty level and the number and variety of symmetries in PR problems. We focus on the most difficult far-field PR (FFPR), and propose a novel method using double deep image priors. In realistic evaluation, our method outper-forms all competing methods by large margins. As a single-instance method, our method requires no training data and minimal hyperparameter tuning… 

Figures and Tables from this paper



Deep Learning Initialized Phase Retrieval

It is shown that a carefully designed deep learning pipeline can consistently generate reliable initialization, so that the subsequent iterative methods can solve the PR problem and produce high-quality solutions.

Deep Iterative Reconstruction for Phase Retrieval

This work develops a phase retrieval algorithm that utilizes two DNNs together with the model-based HIO method that not only achieves state-of-the-art reconstruction performance but also is more robust to different initialization and noise levels.

When deep denoising meets iterative phase retrieval

This work combines iterative methods from phase retrieval with image statistics from deep denoisers, via regularization-by-denoising, and paves the way for hybrid imaging methods that integrate machine-learned constraints in conventional algorithms.

prDeep: Robust Phase Retrieval with a Flexible Deep Network

This work uses the regularization-by-denoising framework and a convolutional neural network denoiser to create prDeep, a new phase retrieval algorithm that is both robust and broadly applicable and test and validate in simulation to demonstrate that it is robust to noise and can handle a variety of system models.

Phase Retrieval using Single-Instance Deep Generative Prior

This work proposes a novel method based on single-instance deep generative prior that works well on complex-valued crystal data and shows promise for phase retrieval on realistic data.

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

This work presents PhaseGAN, a new DL approach based on Generative Adversarial Networks, which allows the use of unpaired datasets and includes the physics of image formation, providing phase reconstructions when conventional phase retrieval algorithms fail.

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.

Early Stopping for Deep Image Prior

This paper proposes an efficient ES strategy, which consistently detects near-peak performance across several vision tasks and DIP variants, and not only outpaces the existing ones—which only work in very narrow domains, but also remains effective when combined with a number of methods that try to mitigate the overfitting.

Phase Retrieval Using Conditional Generative Adversarial Networks

In this paper, we propose the application of conditional generative adversarial networks to solve various phase retrieval problems. We show that including knowledge of the measurement process at

Blind Image Deblurring with Unknown Kernel Size and Substantial Noise

This paper proposes a practical BID method that is stable against both blind deconvolution and substantial noise, and builds on the recent ideas of solving inverse problems by integrating the physical models and structured deep neural networks, without extra training data.