用贝塞尔曲线优化采样路径，10步内生成质量提升2-3倍
BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
- 用贝塞尔函数参数化随机插值调度器，自动满足边界与单调性约束
- 在≤10次评估下，性能比现有方法提升2-3倍，仅需15分钟训练
- 适合希望快速提升扩散模型生成效率的研究者和工程落地场景
我们提出BézierFlow，一种轻量级训练方法，用于预训练扩散模型和流模型的少步生成。BézierFlow在≤10次NFE（数值求解步数）下实现2-3倍性能提升，且仅需15分钟训练。现有轻量级训练方法虽能学习最优时间步，但仅限于ODE离散化。为拓展适用范围，我们提出通过参数化随机插值（SI）调度器来学习最优采样轨迹变换。核心挑战在于设计满足边界条件、可微性和信噪比（SNR）单调性的参数化形式。为此，我们将调度函数表示为贝塞尔函数，控制点自然施加这些性质。问题转化为学习时间区间内的有序点集，控制点的含义从离散时间步变为贝塞尔控制点。在多种预训练扩散模型和流模型上，BézierFlow始终优于先前的时间步学习方法，证明了将搜索空间从离散时间步扩展到贝塞尔轨迹变换的有效性。
原文摘要 · Abstract (English)
We introduce BézierFlow, a lightweight training approach for few-step generation with pretrained diffusion and flow models. BézierFlow achieves a 2-3x performance improvement for sampling with $\leq$ 10 NFEs while requiring only 15 minutes of training. Recent lightweight training approaches have shown promise by learning optimal timesteps, but their scope remains restricted to ODE discretizations. To broaden this scope, we propose learning the optimal transformation of the sampling trajectory by parameterizing stochastic interpolant (SI) schedulers. The main challenge lies in designing a parameterization that satisfies critical desiderata, including boundary conditions, differentiability, and monotonicity of the SNR. To effectively meet these requirements, we represent scheduler functions as Bézier functions, where control points naturally enforce these properties. This reduces the problem to learning an ordered set of points in the time range, while the interpretation of the points changes from ODE timesteps to Bézier control points. Across a range of pretrained diffusion and flow models, BézierFlow consistently outperforms prior timestep-learning methods, demonstrating the effectiveness of expanding the search space from discrete timesteps to Bézier-based trajectory transformations.
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。