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

TL;DR

This paper introduces FPDS, a multimodal, autoregressive approach for incremental floor plan generation inspired by language models, outperforming existing methods in text-to-floorplan tasks and aligning with real-world architectural workflows.

Contribution

The paper presents a novel 'next room prediction' paradigm for floor plan modeling, enabling incremental generation aligned with architectural design processes.

Findings

FPDS achieves competitive performance against diffusion models and Tell2Design.

The approach supports iterative and incremental floor plan development.

Experimental results validate the effectiveness of the next room prediction paradigm.

Abstract

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.