用3D生成模型直接生成物理合理的3D布局，比现有方法快65%且更真实。
Repurposing 3D Generative Model for Autoregressive Layout Generation
- 直接在3D空间中自回归生成布局，显式建模物体间几何与物理关系。
- 在LayoutVLM上实现19%更高物理合理性，计算速度提升65%。
- 适合需要高效生成真实感3D场景的设计师和研究人员。
我们提出LaviGen框架，将3D生成模型重用于3D布局生成。不同于以往从文本描述推断布局的方法，LaviGen直接在原生3D空间中运行，将布局生成建模为自回归过程，显式建模物体间的几何关系与物理约束，生成连贯且物理合理的3D场景。为进一步提升效果，我们设计了一种改进的3D扩散模型，融合场景、物体与指令信息，并采用双引导自滚动蒸馏机制，显著提高效率与空间精度。在LayoutVLM基准上的大量实验表明，LaviGen在3D布局生成性能上优于当前最先进方法，物理合理性高出19%，计算速度加快65%。代码已开源：https://github.com/fenghora/LaviGen。
原文摘要 · Abstract (English)
We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from textual descriptions, LaviGen operates directly in the native 3D space, formulating layout generation as an autoregressive process that explicitly models geometric relations and physical constraints among objects, producing coherent and physically plausible 3D scenes. To further enhance this process, we propose an adapted 3D diffusion model that integrates scene, object, and instruction information and employs a dual-guidance self-rollout distillation mechanism to improve efficiency and spatial accuracy. Extensive experiments on the LayoutVLM benchmark show LaviGen achieves superior 3D layout generation performance, with 19% higher physical plausibility than the state of the art and 65% faster computation. Our code is publicly available at https://github.com/fenghora/LaviGen.
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。