基于视觉-语义事件链条件的物理可信视频生成

中文摘要 AI 辅助

物理可信视频生成（PPVG）旨在合成符合物理原理的视频，但由于自然语言条件的规定不足，该任务仍具挑战性。先进的思维链（CoT）框架会用物理知识增强提示，但这类提示整体描述物理现象，忽略了中间状态和过渡动态。本文将PPVG重新表述为以事件为中心的生成，将物理演化表示为因果关联且受物理约束的事件链。我们的框架包含三个关键模块：（1）物理驱动的事件链推理，该模块将物理现象分解为因果关联的事件，由演化的场景图表示，公式推导的物理量被绑定到相关对象和交互，表征每个事件过渡的方向和大小；（2）过渡感知的路由关键帧条件，该模块将每个事件路由到专门的关键帧合成算子，用于外观变化或对象变换，连续关键帧在去噪过程中作为残差引导注入，实现事件边界状态间的平滑视觉过渡；（3）物理注入的对比语义引导，该模块为无分类器引导构建物理感知的正提示和反事实负提示，引导生成趋向可信动态，远离违反物理的对应结果。在PhyGenBench、VideoPhy、PhyWorldBench和Physics-IQ上的实验表明，我们的框架在不同领域生成的视频具有更优的物理可信性。

英文摘要

Physically Plausible Video Generation (PPVG) seeks to synthesize videos consistent with physical principles, yet remains challenging due to underspecified natural language conditioning. Advanced chain-of-thought (CoT) frameworks augment prompts with physical knowledge. However, such prompts describe physical phenomena holistically, overlooking intermediate states and transition dynamics. In this paper, we reformulate PPVG as event-centric generation by representing physical evolution as a chain of causally connected and physically constrained events. Our framework comprises three key modules: (1) Physics-driven Event Chain Reasoning. This module decomposes physical phenomena into causally connected events represented by evolving scene graphs. Formula-derived physical quantities are bound to relevant objects and interactions, characterizing the direction and magnitude of each event transition. (2) Transition-aware Routed Keyframe Conditioning. This module routes each event to a specialized keyframe synthesis operator for appearance variation or object transformation. Consecutive keyframes are injected as residual guidance during denoising, enabling smooth visual transitions between event-boundary states. (3) Physics-injected Contrastive Semantic Guidance. This module constructs physics-informed positive and counterfactual negative prompts for classifier-free guidance, steering generation toward plausible dynamics and away from physics-violating counterparts. Experiments on PhyGenBench, VideoPhy, PhyWorldBench, and Physics-IQ demonstrate that our framework generates videos with superior physical plausibility across diverse domains.

发表机构

• College of Electronics and Information Engineering, Sichuan University（四川大学电子信息学院）
• School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）
• School of Computer Science, University of Adelaide（阿德莱德大学计算机学院）
• School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）

机构由 AI 辅助整理，请以论文原文为准。