面向逆问题的对偶上升扩散方法
Dual Ascent Diffusion for Inverse Problems
把扩散模型先验下的 MAP 逆问题求解重构成对偶上升优化，可直接替换图像复原（去噪、去模糊、超分、修复）中常用的近似后验采样，在高噪声测量下更稳、更快、更贴合观测。
原文依据 we introduce a new approach to solving MAP problems with diffusion model priors using a dual ascent optimization framework
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论不适定逆问题是天体物理到医学成像等诸多领域中的基础问题。新兴的扩散模型为求解这类问题提供了强大的先验。然而，现有的最大后验（MAP）或后验采样方法依赖不同的计算近似，导致采样结果不准确或次优。为解决这一问题，我们提出一种新方法，利用对偶上升优化框架求解带扩散模型先验的 MAP 问题。在图像复原问题上，我们的框架在多种指标衡量的图像质量上更优，对高水平测量噪声更鲁棒，速度更快，并且所估计的解比当前最先进方法更忠实地反映观测。
英文原文摘要 781 字符
Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a powerful prior for solving these problems. Existing maximum-a-posteriori (MAP) or posterior sampling approaches, however, rely on different computational approximations, leading to inaccurate or suboptimal samples. To address this issue, we introduce a new approach to solving MAP problems with diffusion model priors using a dual ascent optimization framework. Our framework achieves better image quality as measured by various metrics for image restoration problems, it is more robust to high levels of measurement noise, it is faster, and it estimates solutions that represent the observations more faithfully than the state of the art.