prNet：通过随机细化实现数据驱动的相位检索
prNet: Data-Driven Phase Retrieval via Stochastic Refinement
AI总结：
prNet通过随机细化实现数据驱动的相位检索，结合随机采样、学习去噪和模型更新，提升重建的保真度和感知质量。
摘要：
相位检索是一个病态的逆问题，在经典方法和深度学习方法中，难以同时实现测量保真度和感知现实性。我们提出了一种新的相位检索框架，利用兰格-德动态来实现高效的后验采样，产生在失真和感知质量之间显式平衡的重建。与传统方法优先考虑像素级准确性不同，我们的方法通过随机采样、学习去噪和模型更新的原理性组合来导航感知-失真权衡。该框架包含三个复杂度递增的变体，整合了理论支持的兰格-德推断、自适应噪声计划学习、并行重建采样和从经典求解器获得的预热启动。广泛的实验表明，我们的方法在多个基准上都实现了最先进的性能，无论是保真度还是感知质量。源代码和训练模型可在https://github.com/METU-SPACE-Lab/prNet-for-Phase-Retrieval获取。
英文摘要：
Phase retrieval is an ill-posed inverse problem in which classical and deep learning-based methods struggle to jointly achieve measurement fidelity and perceptual realism. 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 methods navigate 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 methods achieve state-of-the-art performance across multiple benchmarks, both in terms of fidelity and perceptual quality. The source code and trained models are available at https://github.com/METU-SPACE-Lab/prNet-for-Phase-Retrieval
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
