prNet: Data-Driven Phase Retrieval via Stochastic Refinement
This addresses the phase retrieval problem for imaging and signal processing applications, offering a novel method to navigate the perception-distortion tradeoff.
The paper tackles the phase retrieval problem by developing a framework that uses Langevin dynamics for posterior sampling, explicitly balancing distortion and perceptual quality in reconstructions. It achieves state-of-the-art performance on multiple benchmarks in terms of both fidelity and perceptual quality.
We propose a novel framework for phase retrieval that leverages Langevin dynamics to enable efficient posterior sampling, yielding reconstructions that explicitly balance distortion and perceptual quality. Unlike conventional approaches that prioritize pixel-wise accuracy, our method navigates the perception-distortion tradeoff through a principled combination of stochastic sampling, learned denoising, and model-based updates. The framework comprises three variants of increasing complexity, integrating theoretically grounded Langevin inference, adaptive noise schedule learning, parallel reconstruction sampling, and warm-start initialization from classical solvers. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple benchmarks, both in terms of fidelity and perceptual quality.