发表机构
ENS de Lyon; CNRS; Université Claude Bernard Lyon 1; Inria; Univ. Bordeaux; Bordeaux INP; IMB(里昂高等师范学校; 法国国家科学研究中心; 里昂第一大学; 法国国家信息与自动化研究所; 波尔多大学; 波尔多国立理工学院; 波尔多数学研究所)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出一种结合递减噪声水平去噪器与定制调度的算法,在贝叶斯框架下证明其收敛到MAP估计,并在不适定逆问题上超越现有收敛方法、媲美最先进经验方法。
AI 中文摘要
预训练去噪器为将图像先验信息纳入恢复算法提供了强大途径。Plug-and-Play和RED方法利用固定噪声水平的去噪器,在一阶优化方案中实现,并具有收敛保证,但在严重不适定的逆问题上往往难以实现高质量重建。相比之下,近期最先进的方法利用基于流或扩散的生成模型导出的去噪器,并沿递减噪声水平序列对其进行评估。虽然这些方法取得了强大的经验性能,但其收敛理论仍然有限。在本文中,我们通过专门设计一种算法来弥合这一差距,该算法将递减噪声水平的去噪器与为确保收敛而定制的调度相结合。从贝叶斯视角出发,我们证明了在适当假设下,我们的方法收敛到最大后验(MAP)估计。随后,我们将我们的方法应用于各种不适定逆问题,并表明它超越了收敛方法,同时与最先进的经验方法相竞争。
英文摘要
Pretrained denoisers provide a powerful way to incorporate image priors into restoration algorithms. Plug-and-Play and RED approaches exploit fixed-noise-level denoisers within first-order optimization schemes, with convergence guarantees, but often struggle to achieve high-quality reconstruction on severely ill-posed inverse problems. In contrast, recent state-of-the-art approaches leverage denoisers derived from flow- or diffusion-based generative models and evaluate them along a sequence of decreasing noise levels. While these methods achieve strong empirical performance, their convergence theory remains limited. In this paper, we bridge this gap by specifically designing an algorithm that combines denoisers at decreasing noise levels with a schedule tailored to ensure convergence. From a Bayesian perspective, we prove that our method converges to a $\textit{Maximum a Posteriori}$ (MAP) estimate, under suitable assumptions. Subsequently, we apply our method to various ill-posed inverse problems and show that it surpasses convergent methods while competing with state-of-the-art empirical ones.