流更直，行更速：基于修正轨迹均值流的高效一步生成建模

摘要

基于流的生成模型近期展现出强大性能，但其采样通常依赖昂贵的常微分方程数值积分。整流流方法通过学习近似笔直的概率路径实现一步采样，但达到这种直线性需要多次计算密集的整流迭代。均值流方法通过直接建模时间平均速度实现一步生成，但在高曲率流上训练时存在收敛缓慢和监督信号嘈杂的问题。为解决这些局限，我们提出整流均值流框架，仅需单次整流步骤即可沿整流轨迹建模平均速度场。该方法在无需完全直线化轨迹的前提下实现高效训练。此外，我们引入一种简单有效的截断启发式策略，旨在降低残余曲率并进一步提升性能。在ImageNet数据集64×64、256×256和512×512分辨率上的大量实验表明，整流均值流在样本质量和训练效率上均优于现有的一步流蒸馏及整流流方法。代码已开源：https://github.com/Xinxi-Zhang/Re-MeanFlow。

English

Flow-based generative models have recently demonstrated strong performance, yet sampling typically relies on expensive numerical integration of ordinary differential equations (ODEs). Rectified Flow enables one-step sampling by learning nearly straight probability paths, but achieving such straightness requires multiple computationally intensive reflow iterations. MeanFlow achieves one-step generation by directly modeling the average velocity over time; however, when trained on highly curved flows, it suffers from slow convergence and noisy supervision. To address these limitations, we propose Rectified MeanFlow, a framework that models the mean velocity field along the rectified trajectory using only a single reflow step. This eliminates the need for perfectly straightened trajectories while enabling efficient training. Furthermore, we introduce a simple yet effective truncation heuristic that aims to reduce residual curvature and further improve performance. Extensive experiments on ImageNet at 64, 256, and 512 resolutions show that Re-MeanFlow consistently outperforms prior one-step flow distillation and Rectified Flow methods in both sample quality and training efficiency. Code is available at https://github.com/Xinxi-Zhang/Re-MeanFlow.

流更直，行更速：基于修正轨迹均值流的高效一步生成建模

Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories

摘要

Support