A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing
In recent years, as machine learning has been widely studied in the field of architecture, scholars have demonstrated that computers can be used to learn the graphical features of building façade generation. However, existing deep learning in façade generation has yet to generate only a single façad...
Published in: | Sustainability |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/su15031816 |
id |
ftmdpi:oai:mdpi.com:/2071-1050/15/3/1816/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2071-1050/15/3/1816/ 2023-08-20T04:05:22+02:00 A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing Da Wan Runqi Zhao Sheng Zhang Hui Liu Lian Guo Pengbo Li Lei Ding agris 2023-01-18 application/pdf https://doi.org/10.3390/su15031816 EN eng Multidisciplinary Digital Publishing Institute Sustainable Urban and Rural Development https://dx.doi.org/10.3390/su15031816 https://creativecommons.org/licenses/by/4.0/ Sustainability; Volume 15; Issue 3; Pages: 1816 deep learning generative adversarial network (GAN) façade generation Pix2Pix generator comparison Text 2023 ftmdpi https://doi.org/10.3390/su15031816 2023-08-01T08:21:40Z In recent years, as machine learning has been widely studied in the field of architecture, scholars have demonstrated that computers can be used to learn the graphical features of building façade generation. However, existing deep learning in façade generation has yet to generate only a single façade, without comprehensive generation of five façades including the roof. Moreover, most of the existing literature has utilized the Pix2Pix algorithm for façade generation experiments, failing to attempt to replace the original generator in Pix2Pix with a different generator for experiments. This study addresses the above issues by collecting and filtering entries from the international Solar Decathlon (SD competition) to obtain a data set. Subsequently, a low-rise residential building façade generation model based on the Pix2Pix neural network was constructed for training and testing. At the same time, the original U-net generator in Pix2Pix was replaced with three different generators, U-net++, HRNet and AttU-net, for training and test results were obtained. The results were evaluated from both subjective and objective aspects and it was found that the AttU-net generative network showed the best comprehensive generation performance for such façades. HRNet is acceptable if there is a need for fast training and generation Text Attu MDPI Open Access Publishing Sustainability 15 3 1816 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
deep learning generative adversarial network (GAN) façade generation Pix2Pix generator comparison |
spellingShingle |
deep learning generative adversarial network (GAN) façade generation Pix2Pix generator comparison Da Wan Runqi Zhao Sheng Zhang Hui Liu Lian Guo Pengbo Li Lei Ding A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing |
topic_facet |
deep learning generative adversarial network (GAN) façade generation Pix2Pix generator comparison |
description |
In recent years, as machine learning has been widely studied in the field of architecture, scholars have demonstrated that computers can be used to learn the graphical features of building façade generation. However, existing deep learning in façade generation has yet to generate only a single façade, without comprehensive generation of five façades including the roof. Moreover, most of the existing literature has utilized the Pix2Pix algorithm for façade generation experiments, failing to attempt to replace the original generator in Pix2Pix with a different generator for experiments. This study addresses the above issues by collecting and filtering entries from the international Solar Decathlon (SD competition) to obtain a data set. Subsequently, a low-rise residential building façade generation model based on the Pix2Pix neural network was constructed for training and testing. At the same time, the original U-net generator in Pix2Pix was replaced with three different generators, U-net++, HRNet and AttU-net, for training and test results were obtained. The results were evaluated from both subjective and objective aspects and it was found that the AttU-net generative network showed the best comprehensive generation performance for such façades. HRNet is acceptable if there is a need for fast training and generation |
format |
Text |
author |
Da Wan Runqi Zhao Sheng Zhang Hui Liu Lian Guo Pengbo Li Lei Ding |
author_facet |
Da Wan Runqi Zhao Sheng Zhang Hui Liu Lian Guo Pengbo Li Lei Ding |
author_sort |
Da Wan |
title |
A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing |
title_short |
A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing |
title_full |
A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing |
title_fullStr |
A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing |
title_full_unstemmed |
A Deep Learning-Based Approach to Generating Comprehensive Building Façades for Low-Rise Housing |
title_sort |
deep learning-based approach to generating comprehensive building façades for low-rise housing |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://doi.org/10.3390/su15031816 |
op_coverage |
agris |
genre |
Attu |
genre_facet |
Attu |
op_source |
Sustainability; Volume 15; Issue 3; Pages: 1816 |
op_relation |
Sustainable Urban and Rural Development https://dx.doi.org/10.3390/su15031816 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/su15031816 |
container_title |
Sustainability |
container_volume |
15 |
container_issue |
3 |
container_start_page |
1816 |
_version_ |
1774715864731353088 |