prNet: Data-Driven Phase Retrieval via Stochastic Refinement
prNet: Data-Driven Phase Retrieval via Stochastic Refinement
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.
Mehmet Onurcan Kaya、Figen S. Oktem
计算技术、计算机技术
Mehmet Onurcan Kaya,Figen S. Oktem.prNet: Data-Driven Phase Retrieval via Stochastic Refinement[EB/OL].(2025-07-13)[2025-08-02].https://arxiv.org/abs/2507.09608.点此复制
评论