用新指标和注意力机制，让自动户型图更多样且贴合建筑边界。
Boundary-Constrained Diffusion Models for Floorplan Generation: Balancing Realism and Diversity
- 提出多样性评分DS，量化约束下的设计多样性。
- 引入边界交叉注意力模块，显著提升布局对建筑边界的贴合度。
- 揭示真实感与多样性间的权衡，适合关注生成质量的建筑师。
扩散模型在自动化户型生成中广受欢迎，能根据用户设定条件生成高度逼真的布局。然而，优化感知指标如弗雷歇初始距离（FID）会导致设计多样性受限。为此，我们提出多样性评分（DS），用于量化固定约束下的布局多样性。此外，为提升几何一致性，引入边界交叉注意力（BCA）模块，实现对建筑边界的条件控制。实验表明，BCA显著改善边界贴合度，而长期训练会引发多样性崩溃，该问题未被FID检测到，凸显真实感与多样性之间的关键权衡。分布外评估进一步揭示模型对数据集先验的依赖，强调在建筑设计任务中需显式平衡保真度、多样性和泛化能力。
原文摘要 · Abstract (English)
Diffusion models have become widely popular for automated floorplan generation, producing highly realistic layouts conditioned on user-defined constraints. However, optimizing for perceptual metrics such as the Fréchet Inception Distance (FID) causes limited design diversity. To address this, we propose the Diversity Score (DS), a metric that quantifies layout diversity under fixed constraints. Moreover, to improve geometric consistency, we introduce a Boundary Cross-Attention (BCA) module that enables conditioning on building boundaries. Our experiments show that BCA significantly improves boundary adherence, while prolonged training drives diversity collapse undiagnosed by FID, revealing a critical trade-off between realism and diversity. Out-Of-Distribution evaluations further demonstrate the models' reliance on dataset priors, emphasizing the need for generative systems that explicitly balance fidelity, diversity, and generalization in architectural design tasks.
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。