用2D蓝图控制3D生成，让物体摆放更合理、出图更快。
Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint
- 用2D布局作蓝图，引导精确的3D场景初始化
- 通过防碰撞优化和实例细化，提升整体布局合理性与视觉质量
- 适合需要可控3D内容生成的设计师或开发者
我们提出 Layout-Your-3D，一种从文本提示中实现可控且组合式3D生成的框架。现有文本到3D的方法常难以生成物体间合理交互的资产，或需繁琐优化。为解决此问题，本方法利用2D布局作为蓝图，实现对3D生成的精准与可信控制。用户可提供2D布局，或由文本描述自动生成。首先基于高效重建模型设计初始化流程，构建粗粒度3D场景；随后引入防碰撞布局优化过程，并进行实例级细化，以确保全局布局一致性和实例外观质量。实验表明，Layout-Your-3D生成的3D资产更合理、视觉更佳，且单次提示生成时间显著减少。此外，该框架可轻松应用于下游任务，如3D编辑与物体插入。项目页面见：https://colezwhy.github.io/layoutyour3d/
原文摘要 · Abstract (English)
We present Layout-Your-3D, a framework that allows controllable and compositional 3D generation from text prompts. Existing text-to-3D methods often struggle to generate assets with plausible object interactions or require tedious optimization processes. To address these challenges, our approach leverages 2D layouts as a blueprint to facilitate precise and plausible control over 3D generation. Starting with a 2D layout provided by a user or generated from a text description, we first create a coarse 3D scene using a carefully designed initialization process based on efficient reconstruction models. To enforce coherent global 3D layouts and enhance the quality of instance appearances, we propose a collision-aware layout optimization process followed by instance-wise refinement. Experimental results demonstrate that Layout-Your-3D yields more reasonable and visually appealing compositional 3D assets while significantly reducing the time required for each prompt. Additionally, Layout-Your-3D can be easily applicable to downstream tasks, such as 3D editing and object insertion. Our project page is available at:https://colezwhy.github.io/layoutyour3d/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。