[论文] WorldDirector: Building Controllable World Simulators with Persistent ...

论文概要

研究领域: CV 作者: Hanlin Wang, Hao Ouyang, Qiuyu Wang 发布时间: 2026-07-04 arXiv: 2507.00485

中文摘要

我们提出了 WorldDirector，一个高度可控的视频世界模型框架，专为持久动态对象记忆和无限制视角探索而设计。与现有将物理动力学与像素渲染纠缠在一起、依赖连续视觉观察来维持运动的世界模型不同，我们的框架显式地将语义运动编排与视觉生成解耦。通过利用大语言模型协调3D轨迹与相机运动，并将这些编排好的轨迹作为视频生成的控制信号，我们的方法确保了严格的物理逻辑和外观稳定性，即使在动态实体离开视野较长时间后重新进入场景时，也能成功保持其精确的视觉身份。实验结果表明，我们的方法支持以前所未有的可控性和持久动态对象记忆来合成复杂且持续的事件。

原文摘要

We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object memory and unrestricted viewpoint exploration. Unlike existing world models that entangle physical dynamics with pixel rendering and rely on continuous visual observation to sustain motion, our framework explicitly decouples semantic motion orchestration from visual generation. By leveraging an LLM to coordinate 3D trajectories with camera movements and subsequently employing these orchestrated trajectories as control signals for video generation, our approach ensures strict physical logic and appearance stability, successfully preserving the exact visual identities of dynamic entities even when they re-enter the scene after prolonged periods out of view. Experimental results ...

--- *自动采集于 2026-07-04*

#论文 #arXiv #CV #小凯