优化扩散模型采样步数，提升生成效率与质量。
Optimizing Few-Step Sampler for Diffusion Probabilistic Model
- 通过理论推导出采样调度的误差上界，支持高效优化。
- 在ImageNet64上，少步采样仍保持高质量生成效果。
- 适合需要快速推理的扩散模型应用开发者。
扩散概率模型（DPM）在生成高质量、多样化图像方面表现出色，但其推理阶段计算成本高昂。生成过程需求解概率流常微分方程（PF-ODE），该过程依赖于对积分区间进行离散化以实现数值逼近，即采样调度。我们发现一阶求解器的解可表示为所有调度时间步模型输出的凸组合。基于此，我们推导出采样调度的离散化误差上界，并采用蒙特卡洛估计实现高效优化。在此基础上，提出两阶段交替优化算法：第一阶段优化预训练DPM的采样调度；第二阶段在选定时间步上进一步微调DPM。在ImageNet64预训练DPM上的实验表明，所提方法在不同采样步数下均持续优于基线。
原文摘要 · Abstract (English)
Diffusion Probabilistic Models (DPMs) have demonstrated exceptional capability of generating high-quality and diverse images, but their practical application is hindered by the intensive computational cost during inference. The DPM generation process requires solving a Probability-Flow Ordinary Differential Equation (PF-ODE), which involves discretizing the integration domain into intervals for numerical approximation. This corresponds to the sampling schedule of a diffusion ODE solver, and we notice the solution from a first-order solver can be expressed as a convex combination of model outputs at all scheduled time-steps. We derive an upper bound for the discretization error of the sampling schedule, which can be efficiently optimized with Monte-Carlo estimation. Building on these theoretical results, we purpose a two-phase alternating optimization algorithm. In Phase-1, the sampling schedule is optimized for the pre-trained DPM; in Phase-2, the DPM further tuned on the selected time-steps. Experiments on a pre-trained DPM for ImageNet64 dataset demonstrate the purposed method consistently improves the baseline across various number of sampling steps.
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。