首篇生成视频镜头运动抄袭检测研究：CineGuard与CineFlow基准

AI 摘要

该论文首次定义并研究生成视频中的「镜头运动抄袭」问题，指出Sora 2、Veo 3.1等生成模型能以近乎零成本模仿Dolly Zoom、Bullet Time等专业镜头运动，而现有基于视觉内容或光流的取证方法无法捕捉这种运动相似性。作者构建了首个镜头运动数据集与基准CineFlow（含11种运动风格），并提出检测方法CineGuard，将流体力学中的涡度引入光流表示以获得空间不变特征，并采用对比学习训练。实验显示其抄袭检测效果比最强基线提升3.02倍，且在生成视频上依然有效。

正文节选

Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos Abstract. Camera motion often reflects directorial intent and requires professional equipment, making it a high value form of intellectual property. However, generative video models can imitate such high value camera motions with simple prompts, while existing similarity detection methods mainly operate on visual content and fail to capture deeper motion similarity. This is mainly because their training dat

发布时间：2026-09-23 12:00

抓取时间：2026-09-22 12:32

来源机构：arXiv