提出可精确计算去噪后验得分的新方法，提升扩散模型无需训练的条件采样效率。
Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
- 利用无条件得分函数推导出可计算的精确后验得分表达式
- 动态调整每步步长，显著降低去噪过程中的误差
- 方法简洁高效，适用于图像修复、超分等任务，步数更少
扩散模型的成功激发了通过无训练引导去噪过程实现条件采样的研究兴趣，以解决图像恢复等逆问题。一类主流方法基于扩散后验采样（DPS），试图直接近似难以求解的后验得分函数。本文提出一种针对纯粹去噪任务的精确后验得分的新表达式，其形式仅依赖于无条件得分函数且可计算。基于该结果，我们分析了DPS在去噪任务中随时间变化的误差，并实时计算最小化误差的步长。实验表明，这些步长可迁移至颜色化、随机补全和超分辨率等相关逆问题。尽管方法简单，性能仍可媲美当前最先进方法，且采样所需时间步数少于DPS。
原文摘要 · Abstract (English)
The success of diffusion models has driven interest in performing conditional sampling via training-free guidance of the denoising process to solve image restoration and other inverse problems. A popular class of methods, based on Diffusion Posterior Sampling (DPS), attempts to approximate the intractable posterior score function directly. In this work, we present a novel expression for the exact posterior score for purely denoising tasks that is tractable in terms of the unconditional score function. We leverage this result to analyze the time-dependent error in the DPS score for denoising tasks and compute step sizes on the fly to minimize the error at each time step. We demonstrate that these step sizes are transferable to related inverse problems such as colorization, random inpainting, and super resolution. Despite its simplicity, this approach is competitive with state-of-the-art techniques and enables sampling with fewer time steps than DPS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。