PnP-CM：一致性模型作为逆问题的即插即用先验
PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems
将一致性模型视为先验的近端算子，嵌入ADMM即插即用框架，为视觉逆问题（如MRI重建、超分、去模糊）提供无需任务特定训练、仅需2-4步NFE的通用求解器。
原文依据 we reinterpret CMs as proximal operators of a prior, enabling their integration into plug-and-play (PnP) frameworks
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散模型已广泛用于求解逆问题，即从给定测量数据的近似后验分布中采样。最近，一致性模型（CMs）被提出，能够从扩散ODE轨迹上的任意点直接预测最终输出，从而仅需少量神经函数评估（NFEs）即可实现高质量采样。CMs也已被用于逆问题，但现有的基于CM的求解器要么需要额外的任务特定训练，要么使用收敛缓慢的数据保真操作，限制了其在大规模问题上的适用性，并使其难以扩展到非线性场景。在本工作中，我们将CMs重新解释为先验的近端算子，使其能够集成到即插即用（PnP）框架中。具体而言，我们提出了PnP-CM，一种基于ADMM的PnP求解器，为求解广泛的逆问题提供了统一框架，并结合噪声扰动和基于动量的更新以提升低NFE区域内的性能。我们在多种线性和非线性逆问题上评估了我们的方法。我们还首次训练并将CMs应用于MRI数据。结果表明，PnP-CM仅需4次NFE即可实现高质量重建，并在2步内产生有意义的结果，突显了其在实际逆问题中的有效性，同时优于现有的基于CM的方法。
英文原文摘要 1444 字符
Diffusion models have found extensive use in solving inverse problems, by sampling from an approximate posterior distribution of data given the measurements. Recently, consistency models (CMs) have been proposed to directly predict the final output from any point on the diffusion ODE trajectory, enabling high-quality sampling in just a few neural function evaluations (NFEs). CMs have also been utilized for inverse problems, but existing CM-based solvers either require additional task-specific training or utilize data fidelity operations with slow convergence, limiting their applicability to large-scale problems and making them difficult to extend to nonlinear settings. In this work, we reinterpret CMs as proximal operators of a prior, enabling their integration into plug-and-play (PnP) frameworks. Specifically, we propose PnP-CM, an ADMM-based PnP solver that provides a unified framework for solving a wide range of inverse problems, and incorporates noise perturbations and momentum-based updates to improve performance in the low-NFE regime. We evaluate our approach on a diverse set of linear and nonlinear inverse problems. We also train and apply CMs to MRI data for the first time. Our results show that PnP-CM achieves high-quality reconstructions in as few as 4 NFEs, and produces meaningful results in 2 steps, highlighting its effectiveness in real-world inverse problems while outperforming existing CM-based approaches.