RoPECraft：基于轨迹引导RoPE优化的无训练运动迁移扩散变换器

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers

May 19, 2025

作者: Ahmet Berke Gokmen, Yigit Ekin, Bahri Batuhan Bilecen, Aysegul Dundar

cs.AI

摘要

我们提出了RoPECraft，一种无需训练的视频运动迁移方法，专为扩散变换器设计，仅通过修改其旋转位置嵌入（RoPE）即可实现。首先，我们从参考视频中提取密集光流，并利用得到的运动偏移量对RoPE的复指数张量进行扭曲，从而将运动有效地编码到生成过程中。随后，在去噪步骤中，通过使用光流匹配目标对预测速度与目标速度之间的轨迹对齐，进一步优化这些嵌入。为了确保输出忠实于文本提示并防止重复生成，我们引入了一个基于参考视频傅里叶变换相位分量的正则化项，将相位角投影到平滑流形上以抑制高频伪影。基准测试实验表明，RoPECraft在定性和定量上均优于所有近期发布的方法。

English

We propose RoPECraft, a training-free video motion transfer method for diffusion transformers that operates solely by modifying their rotary positional embeddings (RoPE). We first extract dense optical flow from a reference video, and utilize the resulting motion offsets to warp the complex-exponential tensors of RoPE, effectively encoding motion into the generation process. These embeddings are then further optimized during denoising time steps via trajectory alignment between the predicted and target velocities using a flow-matching objective. To keep the output faithful to the text prompt and prevent duplicate generations, we incorporate a regularization term based on the phase components of the reference video's Fourier transform, projecting the phase angles onto a smooth manifold to suppress high-frequency artifacts. Experiments on benchmarks reveal that RoPECraft outperforms all recently published methods, both qualitatively and quantitatively.