← 研踪 PaperTrailCVF · CVPR 2026:cvf:3ace07a60db96f2e02b56bec26b54907 · 记录 #1
WorldGen: From Text to Traversable and Interactive 3D Worlds
Wang, DilinJung, HyunyoungMonnier, TomSohn, KihyukZou, ChuhangXiang, XiaoyuYeh, Yu-YingLiu, DiHuang, ZixuanNguyen-Phuoc, ThuFan, YuchenOprea, SergiuWang, ZiyanShapovalov, RomanSarafianos, NikolaosGroueix, ThibaultToisoul, AntoineDhar, PrithvirajChu, XiaoChen, MinghaoPark, Geon YeongRanjan, RakeshVedaldi, Andrea 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 04:13
摘要
We introduce WorldGen, a method for generating large, fully formed, navigable 3D worlds from a single text prompt. Existing approaches to 3D scene generation often trade off scene diversity, completeness, and correctness in different ways. We push this envelope by producing large scenes explicitly decomposed into individual, high-quality 3D meshes, making them compatible with standard game engines. Our approach first uses a language-driven procedural generator to lay out the scene's basic volumes and navigable regions. An image generator then establishes the scene's theme, style, and details. Next, we obtain a high-quality, compositional 3D reconstruction of the planned scene. This step first uses an image-to-3D model to perform a holistic reconstruction that implicitly determines the shape and location of all scene objects, accounting for context and navigability. The reconstruction is then decomposed into individual entities, which are regenerated at higher resolution, synthesizing additional details with guidance from the image generator. We ablate key design choices and compare qualitatively against existing scene generators, showing that our design addresses their gaps.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
WorldGen: From Text to Traversable and Interactive 3D Worlds
We introduce WorldGen, a method for generating large, fully formed, navigable 3D worlds from a single text prompt. Existing approaches to 3D scene generation often trade off scene diversity, completeness, and correctness in different ways. We push this envelope by producing large scenes explicitly decomposed into individual, high-quality 3D meshes, making them compatible with standard game engines. Our approach first uses a language-driven procedural generator to lay out the scene's basic volumes and navigable regions. An image generator then establishes the scene's theme, style, and details. Next, we obtain a high-quality, compositional 3D reconstruction of the planned scene. This step first uses an image-to-3D model to perform a holistic reconstruction that implicitly determines the shape and location of all scene objects, accounting for context and navigability. The reconstruction is then decomposed into individual entities, which are regenerated at higher resolution, synthesizing additional details with guidance from the image generator. We ablate key design choices and compare qualitatively against existing scene generators, showing that our design addresses their gaps.
查看此版本解读 →查看此版本原文 ↗