提出自适应系数加速扩散采样，兼顾速度与生成质量。
Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
- 引入可学习的单步系数，动态调节误差修正强度。
- 5次函数评估下，CIFAR-10 FID达4.18，性能领先。
- 兼容现有求解器，适合追求高效生成的研究者。
基于扩散的生成过程可视为微分方程求解，常需在计算速度与样本质量间权衡。我们对ODE与SDE类求解器的理论分析揭示了其互补缺陷：ODE求解器在确定轨迹上积累不可消除的梯度误差，而SDE方法在步数受限时放大的离散化误差显著。基于此，我们提出AdaSDE，一种新型单步SDE求解器，旨在融合ODE的效率与SDE的误差鲁棒性。具体而言，通过轻量级蒸馏估计每步可学习系数，动态调控误差修正强度以加速扩散采样。该框架可无缝集成至现有求解器中提升性能。大量实验表明其达到当前最优表现：在5次函数评估（NFE）下，于CIFAR-10上取得4.18的FID，FFHQ为8.05，LSUN Bedroom为6.96。代码已开源于https://github.com/WLU-wry02/AdaSDE。
原文摘要 · Abstract (English)
Diffusion-based generative processes, formulated as differential equation solving, frequently balance computational speed with sample quality. Our theoretical investigation of ODE- and SDE-based solvers reveals complementary weaknesses: ODE solvers accumulate irreducible gradient error along deterministic trajectories, while SDE methods suffer from amplified discretization errors when the step budget is limited. Building upon this insight, we introduce AdaSDE, a novel single-step SDE solver that aims to unify the efficiency of ODEs with the error resilience of SDEs. Specifically, we introduce a single per-step learnable coefficient, estimated via lightweight distillation, which dynamically regulates the error correction strength to accelerate diffusion sampling. Notably, our framework can be integrated with existing solvers to enhance their capabilities. Extensive experiments demonstrate state-of-the-art performance: at 5 NFE, AdaSDE achieves FID scores of 4.18 on CIFAR-10, 8.05 on FFHQ and 6.96 on LSUN Bedroom. Codes are available in https://github.com/WLU-wry02/AdaSDE.
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。