StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization

Hugging Face Daily Papers Papers

Summary

StateFlow introduces a state-centric framework for generative previsualization, using a persistent 3D world state to support iterative, controllable scene and camera editing for film and game design.

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.
Original Article
View Cached Full Text

Cached at: 08/13/26, 03:34 PM

Paper page - StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization

Source: https://huggingface.co/papers/2608.12314 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

StateFlow introduces a persistent 3D world state to enable iterative, controllable previsualization for film and game design by constructing, evolving, and accessing structured scene and camera representations.

Previsualizationis 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 orvideo 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, astate-centric frameworkforgenerative 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 forprevisualization. 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-awaredual-view initialization, while State evolution translates user intent intostructured state transitionswhile preserving world memory, avoiding full-scene regeneration for each edit. State access usesrender-feedback reflectionto 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.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2608\.12314

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.12314 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.12314 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.12314 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

CG-World: A Large-Scale World-State Dataset and Protocol for World Models

arXiv cs.AI

CG-World is a large-scale world-state dataset and protocol derived from industrial computer graphics pipelines, explicitly recording multimodal world states, interventions, and counterfactual branches to support world model research. It demonstrates improvements in geometry-conditioned video generation, action prediction, and closed-loop transfer of vision-language-action policies.

From Pixels to States: Rethinking Interactive World Models as Game Engines

Hugging Face Daily Papers

This paper rethinks interactive world models as game engines by examining four key dimensions—action control, state dynamics, state-observation persistence, and real-time generation—and introduces a scalable data engine for Black Myth: Wukong with over 90 hours of gameplay data to advance state-aware game world modeling.