恒定加速流动

摘要

矫正流和回流程序显著推进了快速生成，逐渐使普通微分方程（ODE）流直线化。它们基于这样的假设运行，即图像和噪声对（称为耦合）可以用具有恒定速度的直线轨迹近似。然而，我们观察到，使用恒定速度建模和回流程序在准确学习对之间的直线轨迹方面存在局限，导致在少步生成中表现不佳。为了解决这些局限，我们引入了常加速流（CAF），这是一个基于简单的恒定加速方程的新框架。CAF引入了加速度作为一个额外的可学习变量，允许更具表现力和准确地估计ODE流。此外，我们提出了两种技术来进一步提高估计的准确性：加速度模型的初始速度调节和初始速度的回流过程。我们在玩具数据集、CIFAR-10和ImageNet 64x64上进行的综合研究表明，CAF在一步生成方面优于最先进的基线模型。我们还展示了CAF在保持少步耦合和反演方面相比矫正流有了显著改进。代码可在https://github.com/mlvlab/CAF{https://github.com/mlvlab/CAF}获取。

English

Rectified flow and reflow procedures have significantly advanced fast generation by progressively straightening ordinary differential equation (ODE) flows. They operate under the assumption that image and noise pairs, known as couplings, can be approximated by straight trajectories with constant velocity. However, we observe that modeling with constant velocity and using reflow procedures have limitations in accurately learning straight trajectories between pairs, resulting in suboptimal performance in few-step generation. To address these limitations, we introduce Constant Acceleration Flow (CAF), a novel framework based on a simple constant acceleration equation. CAF introduces acceleration as an additional learnable variable, allowing for more expressive and accurate estimation of the ODE flow. Moreover, we propose two techniques to further improve estimation accuracy: initial velocity conditioning for the acceleration model and a reflow process for the initial velocity. Our comprehensive studies on toy datasets, CIFAR-10, and ImageNet 64x64 demonstrate that CAF outperforms state-of-the-art baselines for one-step generation. We also show that CAF dramatically improves few-step coupling preservation and inversion over Rectified flow. Code is available at https://github.com/mlvlab/CAF{https://github.com/mlvlab/CAF}.

恒定加速流动

Constant Acceleration Flow

摘要

Summary

Support

Support