Directly from Alpha to Omega: Controllable End-to-End Vector Floor Plan Generation

TL;DR

This paper introduces CE2EPlan, a novel end-to-end diffusion model for floor plan generation that offers greater flexibility, diversity, and control compared to traditional multi-step pipeline methods, closely mimicking human design processes.

Contribution

The paper presents a controllable end-to-end diffusion model that directly learns to generate floor plans from data, overcoming limitations of existing multi-step pipeline approaches.

Findings

Outperforms existing multi-step pipeline methods in quality.

Provides higher user control over generated layouts.

Produces more diverse and realistic floor plans.

Abstract

Automated floor plan generation aims to create residential layouts by arranging rooms within a given boundary, balancing topological, geometric, and aesthetic considerations. The existing methods typically use a multi-step pipeline with intermediate representations to decompose the prediction process into several sub-tasks, limiting model flexibility and imposing predefined solution paths. This often results in unreasonable outputs when applied to data unsuitable for these predefined paths, making it challenging for these methods to match human designers, who do not restrict themselves to a specific set of design workflows. To address these limitations, we introduce CE2EPlan, a controllable end-to-end topology- and geometry-enhanced diffusion model that removes restrictions on the generative process of AI design tools. Instead, it enables the model to learn how to design floor plans directly from data, capturing a wide range of solution paths from input boundaries to complete layouts. Extensive experiments demonstrate that our method surpasses all existing approaches using the multi-step pipeline, delivering higher-quality results with enhanced user control and greater diversity in output, bringing AI design tools closer to the versatility of human designers.