CVNov 19, 2024

HouseTune: Two-Stage Floorplan Generation with LLM Assistance

arXiv:2411.12279v44 citationsh-index: 21
Originality Highly original
AI Analysis

This addresses the problem of intuitive and precise floorplan generation for home design applications, offering a user-friendly approach without extensive domain-specific data.

The paper tackles text-to-floorplan generation by proposing a two-stage framework that uses LLMs for initial layout generation and diffusion models for refinement, achieving state-of-the-art performance across all metrics.

This paper proposes a two-stage text-to-floorplan generation framework that combines the reasoning capability of Large Language Models (LLMs) with the generative power of diffusion models. In the first stage, we leverage a Chain-of-Thought (CoT) prompting strategy to guide an LLM in generating an initial layout (Layout-Init) from natural language descriptions, which ensures a user-friendly and intuitive design process. However, Layout-Init may lack precise geometric alignment and fine-grained structural details. To address this, the second stage employs a conditional diffusion model to refine Layout-Init into a final floorplan (Layout-Final) that better adheres to physical constraints and user requirements. Unlike prior methods, our approach effectively reduces the difficulty of floorplan generation learning without the need for extensive domain-specific training data. Experimental results demonstrate that our approach achieves state-of-the-art performance across all metrics, which validates its effectiveness in practical home design applications.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes