arXiv research

DeepPhaseCut uses neural networks to improve Fourier phase retrieval.

Combines deep learning and iterative methods for robust phase retrieval.

We consider the problem of sparse phase retrieval from Fourier transform magnitudes to recover the $k$-sparse signal vector and its support $\mathcal{T}$. We exploit extended support estimate $\mathcal{E}$ with size larger than $k$ satisfying $\mathcal{E} \supseteq \mathcal{T}$ and obtained by a trained deep neural net…

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 training time leads to an optimization at test time that is more robust to initialization than existing approaches involving …

Deep learning tackles low-photon nanoscale holographic phase retrieval.

A new CNN-based algorithm improves Fourier ptychography for faster, more robust image reconstruction.

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 scatt…

Paper tackles image recovery from blurry measurements using deep generative priors.

One of the most powerful approaches to imaging at the nanometer or subnanometer length scale is coherent diffraction imaging using X-ray sources. For amorphous (non-crystalline) samples, the raw data can be interpreted as the modulus of the continuous Fourier transform of the unknown object. Making use of prior informa…

This paper tackles non-convex phase retrieval with structured assumptions.

UPR hybrid model improves phase retrieval performance.

A new deep learning model improves phase retrieval performance.

New algorithms handle phase retrieval with rank d measurements, revealing phase transitions.

Extends phase retrieval methods to handle sensing vector errors.

Can we recover a complex signal from its Fourier magnitudes? More generally, given a set of $m$ measurements, $y_k = |\mathbf a_k^* \mathbf x|$ for $k = 1, \dots, m$, is it possible to recover $\mathbf x \in \mathbb{C}^n$ (i.e., length-$n$ complex vector)? This **generalized phase retrieval** (GPR) problem is a fundame…

Phase retrieval refers to the problem of recovering real- or complex-valued vectors from magnitude measurements. The best-known algorithms for this problem are iterative in nature and rely on so-called spectral initializers that provide accurate initialization vectors. We propose a novel class of estimators suitable fo…

We study the Low Rank Phase Retrieval (LRPR) problem defined as follows: recover an $n \times q$ matrix $X^*$ of rank $r$ from a different and independent set of $m$ phaseless (magnitude-only) linear projections of each of its columns. To be precise, we need to recover $X^*$ from $y_k := |A_k{}' x^*_k|, k=1,2,\dots, q$…

This paper introduces SRPR for robust phase retrieval with smoothed loss functions.

New method uses generative models to improve phase retrieval stability.

New algorithm solves phase retrieval with adaptive stopping criteria.

We consider the problem of compressed sensing and of (real-valued) phase retrieval with random measurement matrix. We derive sharp asymptotics for the information-theoretically optimal performance and for the best known polynomial algorithm for an ensemble of generative priors consisting of fully connected deep neural …

Paper tackles sparse phase retrieval with a novel Bayesian approach.

Descending phase retrieval algorithms show a phase transition with increasing sample complexity.

We consider the robust phase retrieval problem of recovering the unknown signal from the magnitude-only measurements, where the measurements can be contaminated by both sparse arbitrary corruption and bounded random noise. We propose a new nonconvex algorithm for robust phase retrieval, namely Robust Wirtinger Flow to …

Global stability bounds for matrix frames in phase retrieval problems.

Near-optimal sample complexity for phase retrieval with generative priors.

We propose a new algorithm to learn a dictionary for reconstructing and sparsely encoding signals from measurements without phase. Specifically, we consider the task of estimating a two-dimensional image from squared-magnitude measurements of a complex-valued linear transformation of the original image. Several recent …

Paper tackles phase retrieval with robust gradient descent for noisy data.

New method uses image registration to recover complex signals from amplitude data.

Gradient descent variants improve phase retrieval accuracy.

Transformer models improve query-document retrieval efficiency and accuracy.

We propose a flexible convex relaxation for the phase retrieval problem that operates in the natural domain of the signal. Therefore, we avoid the prohibitive computational cost associated with "lifting" and semidefinite programming (SDP) in methods such as PhaseLift and compete with recently developed non-convex techn…

Continuous-time mirror descent solves sparse phase retrieval efficiently.

New findings show sparse signals in MRA model require fewer measurements than previously thought.

Improved regret bounds for bandit phase retrieval.

Phase retrieval algorithms have become an important component in many modern computational imaging systems. For instance, in the context of ptychography and speckle correlation imaging, they enable imaging past the diffraction limit and through scattering media, respectively. Unfortunately, traditional phase retrieval …

Study shows how anisotropic data affects learning dynamics in phase retrieval.

Restricted Boltzmann Machines are described by the Gibbs measure of a bipartite spin glass, which in turn corresponds to the one of a generalised Hopfield network. This equivalence allows us to characterise the state of these systems in terms of retrieval capabilities, both at low and high load. We study the paramagnet…

Study phase retrieval under misspecified models using generative priors.

In this paper we study the property of phase retrievability by redundant sysems of vectors under perturbations of the frame set. Specifically we show that if a set $\fc$ of $m$ vectors in the complex Hilbert space of dimension n allows for vector reconstruction from magnitudes of its coefficients, then there is a pertu…

In this paper, we consider the problem of low-rank phase retrieval whose objective is to estimate a complex low-rank matrix from magnitude-only measurements. We propose a hierarchical prior model for low-rank phase retrieval, in which a Gaussian-Wishart hierarchical prior is placed on the underlying low-rank matrix to …

Solves a challenging problem in imaging and communication.

Optimal spectral initializers impact phase retrieval phase transitions.

The classical shift retrieval problem considers two signals in vector form that are related by a shift. The problem is of great importance in many applications and is typically solved by maximizing the cross-correlation between the two signals. Inspired by compressive sensing, in this paper, we seek to estimate the shi…

We study phase retrieval from magnitude measurements of an unknown signal as an algebraic estimation problem. Indeed, phase retrieval from rank-one and more general linear measurements can be treated in an algebraic way. It is verified that a certain number of generic rank-one or generic linear measurements are suffici…

SpecGD mitigates misalignment in phase retrieval models with anisotropic inputs.

Gradient flow in phase retrieval escapes spurious minima with high probability.

Paper studies early-stopped mirror descent for noisy sparse phase retrieval.