HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation

TL;DR

HypergraphFormer is a novel LLM-based method that generates editable, hypergraph-encoded floor plans, outperforming existing techniques and demonstrating high flexibility and data efficiency across diverse datasets.

Contribution

The paper introduces HypergraphFormer, a hypergraph-based approach for floor plan generation using LLMs, enabling high editability and generalization to irregular boundaries.

Findings

Outperforms state-of-the-art rasterized and vectorized methods.

Demonstrates high data efficiency and robustness under distribution shift.

Enables generation of floor plans for arbitrary, irregular boundaries.

Abstract

In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a large language model (LLM). The model is trained via supervised fine-tuning to generate a hypergraph-based textual representation that encodes spatial relationships and connectivity information within floor plans. We train and evaluate our approach on the RPLAN dataset, and further demonstrate its generalizability on a separate out-of-distribution dataset, which we release in this paper. Our method outperforms state-of-the-art techniques based on rasterized or vectorized representations across a diverse set of metrics. We also show improved data efficiency, particularly under distribution shift. The hypergraph formulation enables the generation of floor plans for arbitrary, irregular, user-specified boundaries by decoupling apartment footprints from their functional and geometric subdivisions. Furthermore, we show that the proposed methodology offers a high degree of editability, making it particularly well suited to design-oriented workflows supported by LLMs.