Multi-Unit Floor Plan Recognition and Reconstruction Using Improved Semantic Segmentation of Raster-Wise Floor Plans

TL;DR

This paper introduces two advanced segmentation methods to convert 2D floor plans into 3D models, enhancing digital twin creation for urban management and emergency planning.

Contribution

It presents novel pixel-wise segmentation techniques based on MDA-Unet and MACU-Net with improvements, enabling effective 3D reconstruction from 2D floor plans.

Findings

Achieved a mean F1 score of 0.86 on the CubiCasa dataset.

Outperformed existing state-of-the-art segmentation methods.

Provided publicly available code to facilitate further research.

Abstract

Digital twins have a major potential to form a significant part of urban management in emergency planning, as they allow more efficient designing of the escape routes, better orientation in exceptional situations, and faster rescue intervention. Nevertheless, creating the twins still remains a largely manual effort, due to a lack of 3D-representations, which are available only in limited amounts for some new buildings. Thus, in this paper we aim to synthesize 3D information from commonly available 2D architectural floor plans. We propose two novel pixel-wise segmentation methods based on the MDA-Unet and MACU-Net architectures with improved skip connections, an attention mechanism, and a training objective together with a reconstruction part of the pipeline, which vectorizes the segmented plans to create a 3D model. The proposed methods are compared with two other state-of-the-art techniques and several benchmark datasets. On the commonly used CubiCasa benchmark dataset, our methods have achieved the mean F1 score of 0.86 over five examined classes, outperforming the other pixel-wise approaches tested. We have also made our code publicly available to support research in the field.