用随机采样平衡图像保真与视觉真实，提升相位恢复效果
prNet: Data-Driven Phase Retrieval via Stochastic Refinement
- 基于Langevin动态实现后验采样，兼顾重建精度与感知质量
- 在多个基准上达到当前最优，同时提升保真度与视觉效果
- 适合需要高质量相位恢复的成像与计算光学研究者
相位恢复是一个病态逆问题，传统方法与基于深度学习的方法难以同时实现测量保真度与感知真实性。本文提出一种新型相位恢复框架，利用Langevin动力学实现高效后验采样，生成在失真与感知质量间明确平衡的重建结果。不同于侧重像素级准确性的常规方法，本方法通过随机采样、学习型去噪与模型驱动更新的合理结合，系统性地权衡感知与失真。框架包含三种逐步复杂的变体，整合了理论基础坚实的Langevin推断、自适应噪声调度学习、并行重建采样及来自经典求解器的热启动初始化。大量实验表明，所提方法在多个基准上均取得当前最优性能，兼具保真度与感知质量。源代码与训练模型见https://github.com/METU-SPACE-Lab/prNet-for-Phase-Retrieval。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。