FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Jun, Zeng, Pengyu, Zhong, Jing, Li, Peilin, Zhang, Miao, Luo, Ran, Lu, Shuai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918111306842112
author Yin, Jun
Zeng, Pengyu
Zhong, Jing
Li, Peilin
Zhang, Miao
Luo, Ran
Lu, Shuai
author_facet Yin, Jun
Zeng, Pengyu
Zhong, Jing
Li, Peilin
Zhang, Miao
Luo, Ran
Lu, Shuai
contents In the architectural design process, floor plan generation is inherently progressive and iterative. However, existing generative models for floor plans are predominantly end-to-end generation that produce an entire pixel-based layout in a single pass. This paradigm is often incompatible with the incremental workflows observed in real-world architectural practice. To address this issue, we draw inspiration from the autoregressive 'next token prediction' mechanism commonly used in large language models, and propose a novel 'next room prediction' paradigm tailored to architectural floor plan modeling. Experimental evaluation indicates that FPDS demonstrates competitive performance in comparison to diffusion models and Tell2Design in the text-to-floorplan task, indicating its potential applicability in supporting future intelligent architectural design.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21562
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction
Yin, Jun
Zeng, Pengyu
Zhong, Jing
Li, Peilin
Zhang, Miao
Luo, Ran
Lu, Shuai
Computation and Language
Artificial Intelligence
Hardware Architecture
In the architectural design process, floor plan generation is inherently progressive and iterative. However, existing generative models for floor plans are predominantly end-to-end generation that produce an entire pixel-based layout in a single pass. This paradigm is often incompatible with the incremental workflows observed in real-world architectural practice. To address this issue, we draw inspiration from the autoregressive 'next token prediction' mechanism commonly used in large language models, and propose a novel 'next room prediction' paradigm tailored to architectural floor plan modeling. Experimental evaluation indicates that FPDS demonstrates competitive performance in comparison to diffusion models and Tell2Design in the text-to-floorplan task, indicating its potential applicability in supporting future intelligent architectural design.
title FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction
topic Computation and Language
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2506.21562