Robust Compressive Phase Retrieval via Deep Generative Priors

Abstract

This paper proposes a new framework to regularize the highly ill-posed and non-linear phase retrieval problem through deep generative priors using simple gradient descent algorithm. We experimentally show effectiveness of proposed algorithm for random Gaussian measurements (practically relevant in imaging through scattering media) and Fourier friendly measurements (relevant in optical set ups). We demonstrate that proposed approach achieves impressive results when compared with traditional hand engineered priors including sparsity and denoising frameworks for number of measurements and robustness against noise. Finally, we show the effectiveness of the proposed approach on a real transmission matrix dataset in an actual application of multiple scattering media imaging.

Preprint. Work in progress

References in corpus (10)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Non-invasive real-time imaging through scattering layers and around corners via speckle correlations
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Compressive Phase Retrieval via Generalized Approximate Message Passing
• On Fienup Methods for Regularized Phase Retrieval
• Compressive Phase Retrieval via Reweighted Amplitude Flow
• Phase retrieval from noisy data based on sparse approximation of object phase and amplitude
• Phase Retrieval Under a Generative Prior
• SUNLayer: Stable denoising with generative networks
• Phase Retrieval via Sparse Wirtinger Flow

Cited by in corpus (9)

• Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
• Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
• Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation
• Phase Retrieval with Holography and Untrained Priors: Tackling the Challenges of Low-Photon Nanoscale Imaging
• Blind Image Deconvolution using Pretrained Generative Priors
• Subsampled Fourier Ptychography using Pretrained Invertible and Untrained Network Priors
• Alternating Phase Projected Gradient Descent with Generative Priors for Solving Compressive Phase Retrieval
• Learning Illumination Patterns for Coded Diffraction Phase Retrieval
• Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior