分离语义与物理优化，多智能体协同生成更真实3D室内布局。
DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis
- 拆分语义与物理优化模块，分别用工具修正抽象关系和空间冲突。
- 在多个数据集上生成布局的连贯性与真实性均达领先水平。
- 适合需要高精度、可扩展3D场景生成的研究者与开发者。
3D室内布局合成对虚拟环境构建至关重要。传统方法因依赖固定数据集而泛化能力差。近期基于LLM与VLM的方法虽提升了语义丰富度，但缺乏稳健灵活的优化能力，导致布局质量不佳。本文提出DisCo-Layout框架，将语义与物理优化解耦并协同管理。语义优化通过语义修正工具（SRT）修复对象间抽象关系；物理优化通过网格匹配算法（PRT）解决具体空间冲突。协作层面采用多智能体架构，包含规划器、设计者与评估者，实现智能调度。实验表明，该框架在多个数据集上生成布局具有高度真实感、一致性与泛化能力。代码将公开。
原文摘要 · Abstract (English)
3D indoor layout synthesis is crucial for creating virtual environments. Traditional methods struggle with generalization due to fixed datasets. While recent LLM and VLM-based approaches offer improved semantic richness, they often lack robust and flexible refinement, resulting in suboptimal layouts. We develop DisCo-Layout, a novel framework that disentangles and coordinates physical and semantic refinement. For independent refinement, our Semantic Refinement Tool (SRT) corrects abstract object relationships, while the Physical Refinement Tool (PRT) resolves concrete spatial issues via a grid-matching algorithm. For collaborative refinement, a multi-agent framework intelligently orchestrates these tools, featuring a planner for placement rules, a designer for initial layouts, and an evaluator for assessment. Experiments demonstrate DisCo-Layout's state-of-the-art performance, generating realistic, coherent, and generalizable 3D indoor layouts. Our code will be publicly available.
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。