用可编辑的3D世界状态，实现影视游戏场景的高效迭代预演。
StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization
- 以持久化的3D世界状态为核心，分阶段构建、演化和访问场景。
- 支持局部修改不重生成，提升编辑效率并保持场景一致性。
- 适合影视动画、游戏开发等需要反复迭代设计的场景。
预可视化是影视、游戏、建筑与城市设计中连接创意与制作的关键环节，使创作者能够迭代优化场景、动作、摄像机及时空动态。然而现有生成方法依赖简单提示词一次性合成图像或视频，控制能力弱，难以支持持续编辑。本质上，世界由具有几何、外观等属性的元素与摄像机组成，不同帧通过共享状态的局部修改或重组生成，大部分状态可复用。因此我们提出，缺失的关键是显式且持久的工作状态。为此，我们提出StateFlow——一种以状态为中心的生成式预可视化框架。不同于一次性生成视频，StateFlow使用可编辑的3D世界组织场景结构、演化过程与摄像机配置，同时借助现成视频模型在需要时提升视觉质量。该世界作为持久的结构化3D状态，包含场景元素与相机配置，是预可视化的核心工作表示。基于此，StateFlow包含三个阶段：状态构建通过先验引导、冲突感知的双视角初始化，将生成的2D内容整合为一致的3D世界；状态演化将用户意图转化为结构化状态转换，保留世界记忆，避免每次编辑都重新生成整个场景；状态访问利用渲染反馈反馈，将相机规划优化为视觉上可行的轨迹，不依赖视觉语言模型语义。实验表明，StateFlow能高效生成高质量3D世界，适用于视频创作与类游戏原型开发。
原文摘要 · Abstract (English)
Previsualization is an intermediate layer between ideas and production in film, games, architecture, and urban design. It lets creators iteratively refine scenes, actions, cameras, and spatial-temporal dynamics. Yet existing generative methods rely on simple prompts to jointly control all of these factors through one-shot image or video synthesis, offering weak controllability and limited support for iterative editing. Fundamentally, a world comprises multiple elements with geometry, appearance, and other attributes, together with cameras. Different frames are produced through local modifications or recombinations of this shared state, which is otherwise largely reused. Therefore, we argue that the missing component is an explicit and persistent working state. To address this, we present StateFlow, a state-centric framework for generative previsualization. Rather than generating videos in one shot, StateFlow uses an editable 3D world to organize scene structure, evolution, and cameras, while off-the-shelf video models enhance visual quality when higher fidelity is desired. This world is maintained as a persistent structured 3D state of scene elements and camera configurations, serving as the core working representation for previsualization. Built on this insight, StateFlow has three stages to construct, evolve, and access the world state. State construction lifts generated 2D content into a coherent 3D world through prior-guided, conflict-aware dual-view initialization, while State evolution translates user intent into structured state transitions while preserving world memory, avoiding full-scene regeneration for each edit. State access uses render-feedback reflection to refine camera plans into visually feasible trajectories, avoiding reliance on VLM semantics alone. Experiments show that StateFlow produces high-quality 3D worlds for video creation and game-like prototyping.
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。