FlowMotion：面向视频运动迁移的免训练流引导
FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
对做视频生成的人，这篇给出了一个免训练的运动控制手段：直接拿 flow-based T2V 模型早期潜变量预测当运动表征，省掉额外构造中间引导的开销；速度正则化稳定优化的做法也可迁移到其他采样期引导任务。
原文依据 early latent predictions inherently encode rich temporal information
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视频运动迁移旨在生成一段继承源视频运动模式、同时渲染新场景的目标视频。现有的免训练方法侧重于基于预训练 T2V 模型的中间输出构建运动引导，这带来了沉重的计算开销和有限的灵活性。本文提出 FlowMotion，一种新颖的免训练框架，通过直接利用基于流的 T2V 模型的预测输出，实现高效且灵活的运动迁移。我们的关键洞见是：早期潜变量预测本身即编码了丰富的时序信息。受此启发，我们提出流引导，即基于潜变量预测提取运动表征，以对齐源视频与生成视频之间的运动模式。我们进一步引入速度正则化策略，以稳定优化并确保平滑的运动演化。由于完全作用于模型预测之上，FlowMotion 相比最优方法在时间与资源效率上更优，同时具备有竞争力的性能。
英文原文摘要 1088 字符
Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of pre-trained T2V models, which results in heavy computational overhead and limited flexibility. In this paper, we present FlowMotion, a novel training-free framework that enables efficient and flexible motion transfer by directly leveraging the predicted outputs of flow-based T2V models. Our key insight is that early latent predictions inherently encode rich temporal information. Motivated by this, we propose flow guidance, which extracts motion representations based on latent predictions to align motion patterns between source and generated videos. We further introduce a velocity regularization strategy to stabilize optimization and ensure smooth motion evolution. By operating purely on model predictions, FlowMotion achieves superior time and resource efficiency as well as competitive performance compared with state-of-the-art methods.