发表机构
University of Bologna（博洛尼亚大学）
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CPF-DDNM，一种无需重训练的推理时策略，通过融合连续后验估计改善扩散模型对不可观测图像结构的恢复，在CT和超分辨率任务上优于DDNM。
AI 中文摘要
解决严重不适定的成像逆问题需要恢复那些由测量值不可观测或弱约束的图像结构。扩散模型为推断此类缺失信息提供了富有表现力的学习先验，而后验采样在逆向过程中融入了测量一致性。然而，标准的扩散后验采样器依赖于瞬时的测量感知估计，没有显式利用先前后验校正所携带的信息。我们引入了连续后验融合去噪扩散零空间模型（CPF-DDNM），这是一种推理时策略，融合连续的测量感知估计以改善不可观测图像结构的扩散恢复，无需重新训练或额外的去噪器评估。我们在DDNM中实例化了这一原理，其范围/零空间分解表明，连续融合保留了测量确定的分量，同时仅作用于先验驱动的零空间估计。因此，我们提供了CPF-DDNM的几何解释和局部误差分析，该分析刻画了最优时间相关融合系数，包括外推区域。在稀疏视图和模拟低剂量计算机断层扫描以及医学图像超分辨率上的实验表明，与DDNM相比有一致的改进，并且与基于扩散的逆求解器相比具有竞争力的性能。
英文摘要
Solving severely ill-posed imaging inverse problems requires recovering image structures that are unobservable or weakly constrained by the measurements. Diffusion models provide expressive learned priors for inferring such missing information, while posterior sampling incorporates measurement consistency along the reverse process. Standard diffusion posterior samplers, however, rely on instantaneous measurement-aware estimates, without explicitly exploiting information carried by previous posterior corrections. We introduce Consecutive Posterior Fusion Denoising Diffusion Null-Space Models (CPF-DDNM), an inference-time strategy that fuses consecutive measurement-aware estimates to improve the diffusive recovery of unobservable image structures, without requiring retraining or additional denoiser evaluations. We instantiate this principle within DDNM, whose range/null-space decomposition reveals that consecutive fusion preserves the measurement-determined component while acting exclusively on the prior-driven null-space estimate. We thus provide a geometric interpretation of CPF-DDNM and a local error analysis that characterizes the optimal time-dependent fusion coefficient, including the extrapolative regime. Experiments on sparse-view and simulated low-dose computed tomography, as well as medical image super-resolution, show consistent improvements over DDNM and competitive performance against diffusion-based inverse solvers.
Comments21 pages, 7 figures, 2 tables
