发表机构
University of Pennsylvania（宾夕法尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对潜在扩散模型逆问题，提出各向异性不确定性感知引导框架ANaLOG，通过学习输入和时间相关的协方差加权引导，理论证明必要性，实验在五个逆问题上提升重建质量且保持效率。
AI 中文摘要
原生潜空间引导是近期利用潜在扩散模型解决逆问题的一种范式。它用基于学习到的潜空间代理计算的高效引导，替代了需要每次解码器传递的图像空间前向模型的重复评估。然而，现有方法在潜空间维度上均匀应用引导，忽略了测量仅沿特定方向具有信息性，以及模型预测的可靠性随输入和时间步变化。我们提出ANaLOG，一个利用预训练潜在扩散模型进行高效不确定性感知引导的框架。ANaLOG通过学习各向异性、输入和时间相关的协方差来建模不确定性，并将其整合到引导机制中，以强调可靠方向并降低不确定方向的权重。我们在线性模型设置下理论分析该框架，并证明各向异性、不确定性感知的加权对于正确采样是必要的，而各向同性引导会导致采样误差。在五个具有挑战性的逆问题上的实验表明，ANaLOG在保持效率的同时，相比现有方法提高了感知重建质量。
英文摘要
Native-latent guidance is a recent paradigm for solving inverse problems with latent diffusion models. It replaces repeated evaluations of the image-space forward model, each requiring a decoder pass, with efficient guidance computed using a learned latent-space surrogate. However, existing methods apply guidance uniformly across latent dimensions, ignoring that measurements are informative only along certain directions and that the reliability of model predictions varies across inputs and timesteps. We propose ANaLOG, a framework for efficient uncertainty-aware guidance with pretrained latent diffusion models. ANaLOG models uncertainty by learning an anisotropic, input- and time-dependent covariance that is integrated into the guidance mechanism to emphasize reliable directions and downweight uncertain ones. We theoretically analyze this framework in a linear model setting and prove that anisotropic, uncertainty-aware weighting is necessary for correct sampling, whereas isotropic guidance induces sampling errors. Experiments across five challenging inverse problems show that ANaLOG improves perceptual reconstruction quality over existing methods while preserving efficiency.
