SceneTeller：语言到3D场景生成
SceneTeller: Language-to-3D Scene Generation
AI总结：
本文提出SceneTeller，一种基于文本的3D房间设计方法，利用上下文学习、CAD模型检索和3D-Gaussian-Splatting风格化技术，根据自然语言提示生成高质量3D场景，并支持外观修改，使普通用户也能轻松进行3D设计。
摘要：
设计高质量的室内3D场景在许多实际应用中非常重要，例如房间规划或游戏开发。传统上，这是一个耗时的过程，既需要艺术技巧又需要熟悉专业软件，使得普通用户难以接触。然而，生成式AI的最新进展为3D设计的民主化奠定了坚实基础。在本文中，我们提出了一种基于文本的3D房间设计的开创性方法。给定一个描述房间中物体放置的自然语言提示，我们的方法会生成与之对应的高质量3D场景。通过额外的文本提示，用户可以更改整个场景或其中单个物体的外观。基于上下文学习、CAD模型检索和基于3D-Gaussian-Splatting的风格化构建，我们的turnkey流水线生成最先进的3D场景，同时即使对新手也易于使用。我们的项目页面可在https://sceneteller.github.io/ 获取。
英文摘要：
Designing high-quality indoor 3D scenes is important in many practical applications, such as room planning or game development. Conventionally, this has been a time-consuming process which requires both artistic skill and familiarity with professional software, making it hardly accessible for layman users. However, recent advances in generative AI have established solid foundation for democratizing 3D design. In this paper, we propose a pioneering approach for text-based 3D room design. Given a prompt in natural language describing the object placement in the room, our method produces a high-quality 3D scene corresponding to it. With an additional text prompt the users can change the appearance of the entire scene or of individual objects in it. Built using in-context learning, CAD model retrieval and 3D-Gaussian-Splatting-based stylization, our turnkey pipeline produces state-of-the-art 3D scenes, while being easy to use even for novices. Our project page is available at https://sceneteller.github.io/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
