几何如何进入生成的运动？
How Does Geometry Enter Generated Motion?
浏览论文内容
中文总结 AI 辅助
本研究通过成对干预实验，发现视频生成模型虽保留几何对运动的塑造，但其状态演化偏离物理定律，且文本和片段长度分别控制轨迹的终点与时间。
中文摘要 AI 辅助
在固定的物理定律下，场景的可见几何决定了运动必须如何变化。我们探究视频生成模型如何实现这种关系。我们固定定律和初始状态，仅改变第一帧中绘制的几何，在匹配的轨道和偏转器族内，并将每个生成的轨迹与该几何的模拟器预测进行比较。成对干预每次只改变一个因素：局部凸起、障碍物高度、提示词、片段长度。在九个图像到视频模型中，几何被保留并塑造运动：球的速度跟随轨道的绘制起伏。物理状态会将这种响应延续下去，而这里生成的运动偏离了定律。平均斜率几乎不加速球，连续接触未能通过一致的状态组合，球前方的编辑在其到达之前就改变了它的运动，且球爬升到高于其释放点的障碍物。两个全局条件组织全局轨迹：文本强烈控制目的地，而片段长度强烈控制开放权重模型中的时间。该模式在拍摄的第一帧中持续存在。因此，当前的视频生成表现为几何条件化的运动合成，其状态演化与固定物理定律的系统性不同。
英文摘要
Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We fix the law and the initial state and change only the geometry drawn in the first frame, within matched families of tracks and deflectors, and compare each generated trajectory with the simulator prediction for that geometry. Paired interventions change one thing at a time: a local bump, the height of a barrier, the words of the prompt, the length of the clip. Across nine image-to-video models, geometry is preserved and shapes the motion: the speed of the ball follows the drawn undulation of a track. A physical state would carry this response forward, and here the generated motion parts from the law. The mean slope barely accelerates the ball, successive contacts fail to compose through a consistent state, an edit ahead of the ball alters its motion before it arrives, and the ball climbs over barriers higher than its release point. Two global conditions organize the global trajectory: text strongly controls the destination, while clip length strongly controls timing in the open-weight models tested. The pattern persists with photographed first frames. Current video generation thus behaves as geometry-conditioned motion synthesis whose evolution of state differs systematically from that of a fixed physical law.
发表机构
- The University of Tokyo（东京大学）
- RWTH Aachen University（亚琛工业大学）
- Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
机构由 AI 辅助整理，请以论文原文为准。
