GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion

2026-07-08

AI Summary

This work addresses the challenges of navigating an expansive design space and achieving efficient generation when manually crafting apartment floor plans that are both functionally rational and aesthetically coherent. To this end, the authors propose a controllable, interactive diffusion-based generative framework that models rooms as spatial Gaussian distributions through Gaussian Room Embeddings (GRE)—a continuous latent representation. The framework incorporates user-specified constraints, such as room type, count, and boundary shape, and leverages a large language model (LLM) to interpret natural language instructions or graphical user interface (GUI) inputs for real-time layout editing and generation. Experiments on the RPLAN dataset demonstrate that the method efficiently produces high-quality, constraint-aware polygonal floor plans with editable structural layouts, effectively bridging AI-driven automation and human creativity.

Abstract

Designing functional and aesthetically coherent floor plans requires exploring a vast space of possible room arrangements, a task that quickly becomes overwhelming for human designers. In this paper, we propose GRE-Diff, a controllable and interactive diffusion-based framework that automates the creation and editing of apartment floor plans under user-specified constraints. By combining AI-generated suggestions with real-time, human-in-the-loop editing, the system enables users to specify room types, room counts, boundary shapes, and editing operations through LLM-parsed instructions or GUI-based interaction. It then generates a diverse set of plausible and well-structured designs for refinement. At the core of our approach is Gaussian Room Embedding (GRE), a continuous latent representation that models each room as a spatial Gaussian distribution capturing its location and extent. Extensive experiments on the RPLAN dataset show that GRE-Diff produces high-quality, constraint-aware, and editable polygonal layouts, offering a practical step toward bridging AI-driven automation and human creativity in spatial design.

Problem

• floor plan generation
• spatial layout design
• room arrangement
• design automation
• human-AI collaboration

Innovation

• Gaussian Room Embedding
• diffusion model
• interactive layout generation
• spatial design automation
• human-in-the-loop editing