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
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and LayoutsZilong Huang, Jun He, Xiaobin Huang, Ziyi Xiong 等CVPR 2026 · 被引用 5 次
- Roomify: Spatially-Grounded Style Transformation for Immersive Virtual EnvironmentsXueyang Wang, Qinxuan Cen, Weitao Bi, Yunxiang Ma 等CHI 2026 · 被引用 1 次
它引用的顶会 Paper91
- Efficient Geometry-aware 3D Generative Adversarial NetworksEric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano 等CVPR 2022 · 被引用 984 次
- CAT3D: Create Anything in 3D with Multi-View Diffusion ModelsRuiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee 等NeurIPS 2024 · 被引用 490 次
- DreamFusion: Text-to-3D using 2D DiffusionBen Poole, Ajay Jain, Jonathan T. Barron, Ben MildenhallICLR 2023 · 被引用 463 次
- Learning Object-Compositional Neural Radiance Field for Editable Scene RenderingBangbang Yang, Yinda Zhang, Yinghao Xu, Yijin Li 等ICCV 2021 · 被引用 305 次
- DUSt3R: Geometric 3D Vision Made EasyShuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii 等CVPR 2024 · 被引用 302 次
相关 Paper
- Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D InpaintingYian Wang, Xiaowen Qiu, Jiageng Liu, Zhehuan Chen 等NeurIPS 2024 · 被引用 48 次
- HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language ModelsHaiyan Jiang, Deyu Zhang, Dongdong Weng, Weitao Song 等CVPR 2026 · 被引用 1 次
- GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian SplattingXiaoyu Zhou, Xingjian Ran, Yajiao Xiong, Jinlin He 等ICML 2024 · 被引用 113 次
- Repurposing 3D Generative Model for Autoregressive Layout GenerationHaoran Feng, Yifan Niu, Zehuan Huang, Yangtian Sun 等CVPR 2026 · 被引用 3 次
- Text2VRScene: Exploring the Framework of Automated Text-driven Generation System for VR ExperienceZhizhuo Yin, Yuyang Wang, Theodoros Papatheodorou, Pan HuiIEEE VR 2024 · 被引用 25 次
