DDRM-PR: Fourier Phase Retrieval using Denoising Diffusion Restoration Models

TL;DR

This paper introduces DDRM-PR, a novel method combining diffusion models with alternating-projection techniques to solve nonlinear phase retrieval problems from intensity-only measurements, demonstrating improved performance in simulations and experiments.

Contribution

It presents a new approach that integrates pretrained diffusion priors with model-based methods for nonlinear phase retrieval, extending the application of DDRM to this challenging problem.

Findings

Enhanced phase retrieval accuracy over traditional methods

Successful application to both simulated and real experimental data

Identification of limitations and potential improvements in the approach

Abstract

Diffusion models have demonstrated their utility as learned priors for solving various inverse problems. However, most existing approaches are limited to linear inverse problems. This paper exploits the efficient and unsupervised posterior sampling framework of Denoising Diffusion Restoration Models (DDRM) for the solution of nonlinear phase retrieval problem, which requires reconstructing an image from its noisy intensity-only measurements such as Fourier intensity. The approach combines the model-based alternating-projection methods with the DDRM to utilize pretrained unconditional diffusion priors for phase retrieval. The performance is demonstrated through both simulations and experimental data. Results demonstrate the potential of this approach for improving the alternating-projection methods as well as its limitations.