发表机构
School of Information Science and Technology, Beijing Foreign Studies University（北京外国语大学信息科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出直接条件转移采样（DCTS），通过随机流近似实现免训练扩散逆求解器的全局校正，在四个逆问题上达到竞争性重建质量并提速16.8倍。
AI 中文摘要
免训练扩散逆求解器通常需要在局部测量引导和昂贵的干净空间后验更新之间进行选择。独立的后续刷新可以通过采样干净条件样本并重新加噪来改善全局校正，但其实际实现需要概率流ODE积分和干净空间马尔可夫链蒙特卡洛（MCMC）。我们提出了直接条件转移采样（DCTS），一种对同一理想刷新目标的直接随机流近似。DCTS不是显式地抽取干净样本，而是沿着一条短内路径估计测量条件下的干净均值，并将高斯源噪声直接传输到下一个噪声状态。一个与去噪器兼容的充分统计量和协方差缩放算子更新使得这种条件均值估计成为可能。在四个逆问题上的实验表明，DCTS在重建质量上具有竞争力，且比竞争方法快高达16.8倍。
英文摘要
Training-free diffusion inverse solvers typically choose between local measurement guidance and costly clean-space posterior updates. Independent posterior refresh can improve global correction by sampling a clean conditional and re-noising it, but its practical realization requires probability-flow ODE integration and clean-space Markov chain Monte Carlo (MCMC). We propose Direct Conditional Transition Sampling (DCTS), a direct stochastic-flow approximation to the same ideal refresh target. Rather than explicitly drawing a clean sample, DCTS estimates the measurement-conditioned clean mean along a short inner path and transports Gaussian source noise directly to the next noisy state. A denoiser-compatible sufficient statistic and a covariance-scaled operator update enable this conditional-mean estimation. Experiments on four inverse problems demonstrate that DCTS achieves competitive reconstruction quality with up to $16.8\times$ speedups over competing methods.
