WorldGen：从文本到可漫游、可交互的三维世界
WorldGen: From Text to Traversable and Interactive 3D Worlds
把「图像生成器提供外观先验 + 图像到3D模型做整体重建 + 逐实体高分辨率重生成」串成一条可复用的场景生成流水线，对做文本驱动3D场景生成和可导航场景重建的人，提供了一个绕开场景不完整/不一致问题的分解-重生成范式。
原文依据 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
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 WorldGen，一种从单条文本提示生成大型、完整成形、可漫游三维世界的方法。现有的三维场景生成方法往往在场景多样性、完整性和正确性之间做出不同取舍。我们推进这一边界，生成显式分解为独立高质量三维网格的大型场景，使其与标准游戏引擎兼容。我们的方法首先使用语言驱动的程序化生成器来布局场景的基本体量和可漫游区域。随后由图像生成器确立场景的主题、风格与细节。接下来，我们对规划好的场景获得高质量的组合式三维重建。该步骤首先使用图像到三维模型进行整体重建，隐式地确定所有场景物体的形状与位置，并兼顾上下文与可漫游性。随后将重建结果分解为独立实体，这些实体以更高分辨率重新生成，并在图像生成器的引导下合成额外细节。我们消融了关键设计选择，并与现有场景生成器进行定性比较，表明我们的设计弥补了它们的不足。
英文原文摘要 1193 字符
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.