about
WorldGen: From Text to Traversable and Interactive 3D Worlds (arxiv.org)
2 points by PaulHoule 271 days ago | hide | past | pdf | discuss on HN

In plain words: WorldGen turns a description into a 3D world you can walk through and edit in a game engine: a language model plans where things go, then generation and assembly build it. Instead of hand-modeling objects, it makes navigable worlds that run in real time.

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.

Dilin Wang, Hyunyoung Jung, Tom Monnier, Kihyuk Sohn, Chuhang Zou, Xiaoyu Xiang, Yu-Ying Yeh, Di Liu, Zixuan Huang, Thu Nguyen-Phuoc, Yuchen Fan, Sergiu Oprea, et al.
arXiv:2511.16825 · cs.CV, cs.AI · submitted Nov 20, 2025
abstract · pdf · html

add comment on HN