Boundary-Constrained Diffusion Models for Floorplan Generation: Balancing Realism and Diversity

2026-02-02

AI Summary

Existing automatic floorplan generation methods often sacrifice diversity by over-optimizing for realism and struggle to maintain geometric consistency between layouts and architectural boundaries. This work proposes a diffusion model integrated with boundary constraints, introducing a Boundary Cross-Attention (BCA) mechanism to enhance alignment between generated layouts and building boundaries, alongside a Diversity Score (DS) to explicitly quantify the trade-off between realism and diversity. Experiments demonstrate that BCA significantly improves boundary adherence; however, prolonged training tends to induce diversity collapse—a phenomenon undetected by conventional metrics such as FID. Furthermore, out-of-distribution evaluation reveals limited model generalization, underscoring the necessity of jointly optimizing fidelity, diversity, and generalization capability in floorplan synthesis.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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 Fr\'echet 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.

Problem

• floorplan generation
• diffusion models
• design diversity
• realism-diversity trade-off
• boundary constraints

Innovation

• Diversity Score
• Boundary Cross-Attention
• Diffusion Models
• Floorplan Generation
• Realism-Diversity Trade-off