We're Building a Wall - Size-Invariant Semantic Segmentation of Floor Plan Images
(2026) In Master's Thesis in Mathematical Sciences FMAM05 20252Mathematics (Faculty of Engineering)
- Abstract
- The automation of floor plan interpretation and reconstruction is a key challenge in architectural visualization workflows, particularly when handling heterogeneous, real world data. This thesis project investigates the use of deep learning–based semantic segmentation combined with geometry-aware postprocessing to automate the extraction of structural elements from floor plan images. The work is motivated by an industrial use case at NORNORM, where manual annotation of customer-provided floor plans represents a significant bottleneck in the generation of 3D visualizations.
A convolutional neural network based on a UNet architecture with a pretrained ResNet backbone is developed to segment walls, windows, and doors from floor plan... (More) - The automation of floor plan interpretation and reconstruction is a key challenge in architectural visualization workflows, particularly when handling heterogeneous, real world data. This thesis project investigates the use of deep learning–based semantic segmentation combined with geometry-aware postprocessing to automate the extraction of structural elements from floor plan images. The work is motivated by an industrial use case at NORNORM, where manual annotation of customer-provided floor plans represents a significant bottleneck in the generation of 3D visualizations.
A convolutional neural network based on a UNet architecture with a pretrained ResNet backbone is developed to segment walls, windows, and doors from floor plan images. Special attention is given to dataset-related challenges, including large variations in image scale, annotation quality, class imbalance, and the presence of corrupted data. Multiple preprocessing strategies are evaluated to analyze their impact on model performance and generalization. In addition, the effect of augmenting proprietary data with the public CubiCasa5k dataset is examined.
Beyond pixel-wise segmentation, a postprocessing pipeline is introduced to convert raster predictions into structured, vector-based geometric representations suitable for downstream 3D reconstruction. This pipeline integrates skeletonization, graph-based path extraction, and line simplification using the Ramer-Douglas-Peucker algorithm, producing clean and scalable geometric outputs. Model performance is assessed using standard segmentation metrics as well as uncertainty measures to estimate prediction reliability in deployment scenarios without target annotations available.
The results demonstrate that models trained on tiled images yields the most robust performance across diverse inputs. The proposed system shows strong potential to significantly reduce manual effort while maintaining high accuracy, supporting scalable and sustainable architectural visualization workflows. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9220641
- author
- Duberg, Stina LU and Bernhardtz, Carl
- supervisor
- organization
- course
- FMAM05 20252
- year
- 2026
- type
- H2 - Master's Degree (Two Years)
- subject
- publication/series
- Master's Thesis in Mathematical Sciences
- report number
- 2026:E4
- ISSN
- 1404-6342
- other publication id
- LUTFMA-3604-2026
- language
- English
- id
- 9220641
- date added to LUP
- 2026-02-12 09:23:04
- date last changed
- 2026-02-12 09:23:48
@misc{9220641,
abstract = {{The automation of floor plan interpretation and reconstruction is a key challenge in architectural visualization workflows, particularly when handling heterogeneous, real world data. This thesis project investigates the use of deep learning–based semantic segmentation combined with geometry-aware postprocessing to automate the extraction of structural elements from floor plan images. The work is motivated by an industrial use case at NORNORM, where manual annotation of customer-provided floor plans represents a significant bottleneck in the generation of 3D visualizations.
A convolutional neural network based on a UNet architecture with a pretrained ResNet backbone is developed to segment walls, windows, and doors from floor plan images. Special attention is given to dataset-related challenges, including large variations in image scale, annotation quality, class imbalance, and the presence of corrupted data. Multiple preprocessing strategies are evaluated to analyze their impact on model performance and generalization. In addition, the effect of augmenting proprietary data with the public CubiCasa5k dataset is examined.
Beyond pixel-wise segmentation, a postprocessing pipeline is introduced to convert raster predictions into structured, vector-based geometric representations suitable for downstream 3D reconstruction. This pipeline integrates skeletonization, graph-based path extraction, and line simplification using the Ramer-Douglas-Peucker algorithm, producing clean and scalable geometric outputs. Model performance is assessed using standard segmentation metrics as well as uncertainty measures to estimate prediction reliability in deployment scenarios without target annotations available.
The results demonstrate that models trained on tiled images yields the most robust performance across diverse inputs. The proposed system shows strong potential to significantly reduce manual effort while maintaining high accuracy, supporting scalable and sustainable architectural visualization workflows.}},
author = {{Duberg, Stina and Bernhardtz, Carl}},
issn = {{1404-6342}},
language = {{eng}},
note = {{Student Paper}},
series = {{Master's Thesis in Mathematical Sciences}},
title = {{We're Building a Wall - Size-Invariant Semantic Segmentation of Floor Plan Images}},
year = {{2026}},
}