{"slug": "gre-diff-gaussian-room-embeddings-for-structured-layout-diffusion", "title": "GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion", "summary": "Researchers propose GRE-Diff, a diffusion-based framework that automates floor plan creation and editing under user constraints, using Gaussian Room Embeddings to model rooms as spatial distributions. The system generates diverse, constraint-aware layouts and supports real-time human-in-the-loop editing via LLM-parsed instructions or GUI interaction, demonstrating high-quality results on the RPLAN dataset.", "body_md": "arXiv:2607.08086v1 Announce Type: new\nAbstract: 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.\nBy 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.\nIt then generates a diverse set of plausible and well-structured designs for refinement.\nAt 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.\nExtensive 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.", "url": "https://wpnews.pro/news/gre-diff-gaussian-room-embeddings-for-structured-layout-diffusion", "canonical_source": "https://arxiv.org/abs/2607.08086", "published_at": "2026-07-10 04:00:00+00:00", "updated_at": "2026-07-10 04:22:06.487690+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "computer-vision"], "entities": ["GRE-Diff", "RPLAN"], "alternates": {"html": "https://wpnews.pro/news/gre-diff-gaussian-room-embeddings-for-structured-layout-diffusion", "markdown": "https://wpnews.pro/news/gre-diff-gaussian-room-embeddings-for-structured-layout-diffusion.md", "text": "https://wpnews.pro/news/gre-diff-gaussian-room-embeddings-for-structured-layout-diffusion.txt", "jsonld": "https://wpnews.pro/news/gre-diff-gaussian-room-embeddings-for-structured-layout-diffusion.jsonld"}}