用对偶上升法优化扩散模型，提升图像修复质量与噪声鲁棒性。
Dual Ascent Diffusion for Inverse Problems
- 基于对偶上升框架，优化扩散模型先验下的最大后验估计。
- 在多种指标上优于现有方法，尤其在高噪声下表现更优。
- 适合医学影像、天体物理等需要高精度重建的领域。
病态逆问题在天体物理、医学成像等领域普遍存在。新兴的扩散模型为解决这些问题提供了强大先验。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，导致样本不准确或次优。为此，本文提出一种基于对偶上升优化框架的新方法，用于求解具有扩散模型先验的MAP问题。该方法在图像修复任务中，各项评价指标均优于现有技术，对高噪声测量更具鲁棒性，计算更快，且生成的解能更忠实反映观测数据。
原文摘要 · Abstract (English)
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.
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。