智能设计师：用于结构感知室内布局生成的渐进式多智能体协作
Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation
浏览论文内容
中文总结 AI 辅助
针对室内布局生成难题，提出智能设计师这一渐进式多智能体框架，将布局生成视为迭代约束验证决策过程，通过渐进共识机制协调三个智能体，经实验验证其显著优于现有方法，提升了结构遵循和功能设计连贯性。
中文摘要 AI 辅助
在自动化空间设计中，生成严格遵循建筑约束（如墙壁、门窗）的逼真室内家具布局仍是一项重大挑战。现有方法主要基于扩散模型或大语言模型的一次性生成，缺乏中间几何约束验证机制，在复杂房间约束下常导致结构冲突和功能不可行的布局。为应对这些挑战，我们提出了智能设计师，这是一个渐进式多智能体框架，将结构感知室内布局生成制定为一个迭代且经约束验证的决策过程。该框架通过渐进共识机制协调生成器、评估器和优化器三个专门智能体，在每次放置前进行逐步几何验证和校正，防止错误累积。为促进这种结构感知范式并规范评估，我们建立了InStruct基准，它集成了一个包含超过18000个高质量、参数化注释样本的数据集以及一套新的以结构为中心的指标。广泛的定量评估、定性分析和用户研究表明，智能设计师显著优于现有方法，在严格的结构遵循和功能设计连贯性方面有大幅提升。
英文摘要
Generating realistic interior furniture layouts that strictly adhere to architectural constraints (e.g., walls, doors, and windows) remains a fundamental challenge in automated spatial design. Existing approaches, primarily based on one-shot generation using diffusion models or Large Language Models (LLMs), lack explicit mechanisms for intermediate geometric constraint verification, often resulting in structural collisions and functionally infeasible arrangements under complex room constraints. To address these challenges, we propose Agentic Designer, a progressive, multi-agent framework that formulates structure-aware interior layout generation as an iterative and constraint-verified decision process. By decomposing layout synthesis into modular stages of proposal, verification, and adjustment, the framework coordinates three specialized agents, a Generator, an Evaluator, and a Refiner, through a Progressive Consensus Mechanism. This mechanism enforces stepwise geometric validation and correction before each placement is committed, thereby preventing error accumulation. To facilitate this structure-aware paradigm and standardize evaluation, we establish InStruct, a comprehensive benchmark that integrates a dataset comprising over 18,000 high-quality, parametrically annotated samples with a novel suite of structure-centric metrics. Extensive quantitative evaluations, qualitative analyses, and user studies show that Agentic Designer significantly outperforms state-of-the-art methods, demonstrating substantial improvements in strict structural adherence and functional design coherence.
发表机构
- Guangdong University of Technology（广东工业大学）
- South China University of Technology（华南理工大学）
机构由 AI 辅助整理，请以论文原文为准。
