无需训练，通过调整旋转位置编码实现视频动作迁移。
RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
- 仅修改扩散模型的旋转位置编码，用光流引导运动信息注入。
- 在去噪过程中通过速度对齐优化轨迹，生成更自然的动作序列。
- 抑制高频伪影并保持文本一致性，适合视频生成与动画创作。
我们提出RoPECraft，一种针对扩散变压器的无训练视频动作迁移方法，仅通过修改其旋转位置编码（RoPE）实现。首先从参考视频中提取密集光流，利用运动偏移对RoPE的复指数张量进行形变，将运动信息编码进生成过程。随后在去噪时间步中，通过光流匹配目标速度与预测速度之间的轨迹对齐，进一步优化嵌入。为保证输出与文本提示一致并避免重复生成，引入基于参考视频傅里叶变换相位分量的正则项，将相位角投影至平滑流形以抑制高频伪影。在多个基准上的实验表明，RoPECraft在定性和定量上均优于近期所有方法。
原文摘要 · Abstract (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.
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。