WorldGen: From Text to Traversable and Interactive 3D Worlds

TL;DR

WorldGen is a system that automatically creates large, interactive 3D worlds from text prompts, enabling easy, high-quality virtual environment generation without manual modeling.

Contribution

It introduces a modular pipeline combining language reasoning, procedural, and diffusion-based 3D generation to produce coherent, textured worlds from natural language descriptions.

Findings

Generates traversable, textured 3D worlds from text prompts

Supports real-time rendering and editing in game engines

Bridges the gap between creative intent and virtual environment creation

Abstract

We introduce WorldGen, a system that enables the automatic creation of large-scale, interactive 3D worlds directly from text prompts. Our approach transforms natural language descriptions into traversable, fully textured environments that can be immediately explored or edited within standard game engines. By combining LLM-driven scene layout reasoning, procedural generation, diffusion-based 3D generation, and object-aware scene decomposition, WorldGen bridges the gap between creative intent and functional virtual spaces, allowing creators to design coherent, navigable worlds without manual modeling or specialized 3D expertise. The system is fully modular and supports fine-grained control over layout, scale, and style, producing worlds that are geometrically consistent, visually rich, and efficient to render in real time. This work represents a step towards accessible, generative world-building at scale, advancing the frontier of 3D generative AI for applications in gaming, simulation, and immersive social environments.