Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.12279 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916647664615424 |
|---|---|
| author | Zong, Ziyang Chen, Guanying Zhan, Zhaohuan Yu, Fengcheng Tan, Guang |
| author_facet | Zong, Ziyang Chen, Guanying Zhan, Zhaohuan Yu, Fengcheng Tan, Guang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_12279 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HouseTune: Two-Stage Floorplan Generation with LLM Assistance Zong, Ziyang Chen, Guanying Zhan, Zhaohuan Yu, Fengcheng Tan, Guang Computer Vision and Pattern Recognition 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. |
| title | HouseTune: Two-Stage Floorplan Generation with LLM Assistance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.12279 |