prNet: Data-Driven Phase Retrieval via Stochastic Refinement

doi:10.1109/tci.2026.3719489

prNet: Data-Driven Phase Retrieval via Stochastic Refinement

2026-08-03

0

PRE

AI

DOI：10.1109/tci.2026.3719489

Original

Original request for help

Save

Abstract

En 中文

Phase retrieval is an ill-posed inverse problem in which existing methods often struggle to balance reconstruction fidelity and perceptual quality. We propose a novel Langevin-based framework for phase retrieval that bridges model-driven and data-driven approaches by combining stochastic posterior sampling, learned denoising, and model-based updates to better navigate the perception-distortion tradeoff. The framework consists of three progressively more advanced variants. The first, prNet-Small, provides a theoretically grounded and lightweight pipeline that integrates Langevin dynamics with learned noise and denoising processes and alternating projection-based updates. Building upon this foundation, prNet-Large exploits parallel sampling of diverse reconstructions and aggregates them to approximate the MMSE solution, significantly improving distortion metrics. Finally, prNet-Large-Adversarial enhances perceptual quality by replacing simple averaging with an adversarially trained aggregation network while preserving reconstruction fidelity. In addition, we incorporate test time augmentation to further improve the performance. Extensive experiments demonstrate that the proposed framework consistently outperforms classical, deep learning-based, and diffusion-based baselines across multiple benchmarks in both reconstruction fidelity and perceptual quality.

Keywords:

Phase retrieval

diffusion models

deep learning

nonlinear inverse problems

prNet: Data-Driven Phase Retrieval via Stochastic Refinement

Abstract

Journal

Organization

Cited Papers