arXiv:2606.00499cs.CV2026-06

让视频生成具备物理合理性,自动规划安全高效的运动轨迹。

OptiWorld: Optimal Control for Video World Generation under Physical Constraints

论文配图:OptiWorld: Optimal Control for Video World Generation under Physical Constraints
图 1 · 摘自论文原文
  • 引入最优控制理论,在生成时动态规划受物理约束的轨迹。
  • 在目标引导生成等任务中,视频运动更平滑、安全且符合物理规律。
  • 适合需要真实动力学模拟的场景,如机器人路径规划、影视特效编辑。

视频生成模型正成为可扩展的世界模型形式,但目前主要生成看似合理的运动,而非主动控制或优化底层动力学。因此,生成视频中的物体可能遵循不安全、不平滑、低效或物理上不一致的轨迹。本文提出 extbf{OptiWorld},一个在推理阶段引入经典最优控制的视频世界生成框架。OptiWorld 首先提取紧凑的任务相关世界状态,然后在物理约束下规划最优轨迹,并最终根据该轨迹渲染视频。我们将规划建模为连续流形上的几何问题,将三维几何与任务相关的物理约束统一为规划几何。通过增加这一最优控制层,OptiWorld 生成的视频展现出更优的动力学特性,在目标条件图像到视频生成、视频动力学编辑和反事实生成等多个任务中均表现出色。

原文摘要 · Abstract (English)

Video generation models are becoming a scalable form of world models, but they mainly generate plausible motion rather than proactively control or optimize the underlying dynamics. As a result, an object in the generated video may follow trajectories that are unsafe, not smooth, inefficient, or physically inconsistent. In this work, we propose \textbf{OptiWorld}, a framework that brings classical optimal control into video generation at inference time. OptiWorld first extracts a compact, task-relevant world state, then plans an optimal trajectory under physical constraints, and finally renders the video conditioned on this trajectory. We formulate planning as a geometric problem on a continuous manifold, which converts 3D geometry and task-dependent physical constraints into a unified planning geometry. By adding this optimal-control layer, OptiWorld generates videos with preferable dynamics, demonstrating strong potential in multiple tasks including goal-conditioned image-to-video generation, video dynamics editing, and counterfactual generation.

视频生成最优控制物理模拟

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。