WorldGen: From Text to Traversable and Interactive 3D Worlds
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
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 7f86aad9-a890-40a2-8cd6-79661854c320Cited by top-tier papers2
- MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and LayoutsZilong Huang, Jun He, Xiaobin Huang, Ziyi Xiong et al.CVPR 2026 · 5 citations
- Roomify: Spatially-Grounded Style Transformation for Immersive Virtual EnvironmentsXueyang Wang, Qinxuan Cen, Weitao Bi, Yunxiang Ma et al.CHI 2026 · 1 citation
Builds on91
- Efficient Geometry-aware 3D Generative Adversarial NetworksEric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano et al.CVPR 2022 · 984 citations
- CAT3D: Create Anything in 3D with Multi-View Diffusion ModelsRuiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee et al.NeurIPS 2024 · 490 citations
- DreamFusion: Text-to-3D using 2D DiffusionBen Poole, Ajay Jain, Jonathan T. Barron, Ben MildenhallICLR 2023 · 463 citations
- Learning Object-Compositional Neural Radiance Field for Editable Scene RenderingBangbang Yang, Yinda Zhang, Yinghao Xu, Yijin Li et al.ICCV 2021 · 305 citations
- DUSt3R: Geometric 3D Vision Made EasyShuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii et al.CVPR 2024 · 302 citations
Related papers
- Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D InpaintingYian Wang, Xiaowen Qiu, Jiageng Liu, Zhehuan Chen et al.NeurIPS 2024 · 48 citations
- HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language ModelsHaiyan Jiang, Deyu Zhang, Dongdong Weng, Weitao Song et al.CVPR 2026 · 1 citation
- GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian SplattingXiaoyu Zhou, Xingjian Ran, Yajiao Xiong, Jinlin He et al.ICML 2024 · 113 citations
- Repurposing 3D Generative Model for Autoregressive Layout GenerationHaoran Feng, Yifan Niu, Zehuan Huang, Yangtian Sun et al.CVPR 2026 · 3 citations
- Text2VRScene: Exploring the Framework of Automated Text-driven Generation System for VR ExperienceZhizhuo Yin, Yuyang Wang, Theodoros Papatheodorou, Pan HuiIEEE VR 2024 · 25 citations
