Unified Vector Floorplan Generation via Markup Representation

TL;DR

This paper introduces FML, a unified markup language for floorplan generation, and a transformer model FMLM that outperforms previous methods across diverse generation tasks.

Contribution

The paper proposes a novel unified representation FML and a transformer-based model FMLM for flexible, high-quality floorplan generation from various inputs.

Findings

FMLM surpasses previous state-of-the-art methods on the RPLAN dataset.

FML enables a single model to handle multiple diverse floorplan generation tasks.

FMLM produces high-fidelity, functional floorplans under various conditions.

Abstract

Automatic residential floorplan generation has long been a central challenge bridging architecture and computer graphics, aiming to make spatial design more efficient and accessible. While early methods based on constraint satisfaction or combinatorial optimization ensure feasibility, they lack diversity and flexibility. Recent generative models achieve promising results but struggle to generalize across heterogeneous conditional tasks, such as generation from site boundaries, room adjacency graphs, or partial layouts, due to their suboptimal representations. To address this gap, we introduce Floorplan Markup Language (FML), a general representation that encodes floorplan information within a single structured grammar, which casts the entire floorplan generation problem into a next token prediction task. Leveraging FML, we develop a transformer-based generative model, FMLM, capable of producing high-fidelity and functional floorplans under diverse conditions. Comprehensive experiments on the RPLAN dataset demonstrate that FMLM, despite being a single model, surpasses the previous task-specific state-of-the-art methods.