视频生成中的运动归因

摘要

尽管视频生成模型发展迅猛，但数据对运动特性的影响机制仍不明确。我们提出Motive（视频生成运动归因框架），这一基于梯度的运动中心化数据归因框架可适配现代大规模高质量视频数据集与模型。通过该框架，我们系统分析了哪些微调片段会增强或削弱时序动态效果。Motive通过运动加权损失掩码将时序动态与静态外观分离，实现了高效可扩展的运动特性影响力计算。在文本到视频模型中，Motive能精准识别对运动特征有显著影响的视频片段，并指导数据筛选以提升时间连贯性与物理合理性。采用Motive筛选的高影响力数据后，我们的方法在VBench评测中同时提升了运动平滑度与动态幅度，相比预训练基础模型获得74.1%的人类偏好胜率。据我们所知，这是首个针对视频生成模型进行运动特性（而非视觉外观）归因的框架，并首次将其应用于微调数据筛选。

English

Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework that scales to modern, large, high-quality video datasets and models. We use this to study which fine-tuning clips improve or degrade temporal dynamics. Motive isolates temporal dynamics from static appearance via motion-weighted loss masks, yielding efficient and scalable motion-specific influence computation. On text-to-video models, Motive identifies clips that strongly affect motion and guides data curation that improves temporal consistency and physical plausibility. With Motive-selected high-influence data, our method improves both motion smoothness and dynamic degree on VBench, achieving a 74.1% human preference win rate compared with the pretrained base model. To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models and to use it to curate fine-tuning data.

视频生成中的运动归因

Motion Attribution for Video Generation

摘要

Support