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

2026-02-16

IEEE Transactions on Visualization and Computer Graphics

AI Summary

Existing automatic floorplan generation methods often rely on multi-stage pipelines and intermediate representations, limiting their ability to handle unconventional inputs and constraining design flexibility. This work proposes CE2EPlan, a controllable end-to-end diffusion model that directly generates complete vectorized floorplans from building boundaries, eschewing traditional stepwise strategies. By integrating topology- and geometry-aware enhancement mechanisms with vector-based representation and end-to-end training, the approach achieves high-fidelity outputs while significantly improving generation diversity and user controllability. The method thus better emulates the adaptive and creative capabilities of human designers in architectural layout synthesis.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Diffusion Models for Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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 geometryenhanced 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.

Problem

• floor plan generation
• end-to-end modeling
• design flexibility
• multi-step pipeline
• AI design tools

Innovation

• end-to-end
• diffusion model
• floor plan generation
• controllable generation
• topology-geometry enhancement