IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE

Wenli Liu; Zhaoji Wu; Jack C.P. Cheng; Helen H.L. Kwok; Xingyu Tao

doi:10.35490/EC3.2025.235

IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE

Wenli Liu
, Zhaoji Wu
, Jack C.P. Cheng
, Helen H.L. Kwok
, Xingyu Tao

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

The performance evaluation is crucial in comparing multiple house plans during the early stages. However, simulation-based methods often face challenges such as time consumption and complex modeling processes. Therefore, this paper extracted the features from house plans and proposed an image-based algorithm for automatic geometric simulation modeling. The algorithm successfully modeled 16,000 house plans and obtained simulation results for their energy consumption, indoor thermal comfort, and daylighting. This paper further compares the MARS-based and XGBoost-based surrogate models for performance evaluation using the house plan dataset. The results indicate that XGBoost performed better on all metrics.

Original language	English
Title of host publication	Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025
Editors	Ekaterina Petrova, Marijana Srećković, Pedro Meda, Ranjith K. Soman, Daniel Hall, Jakob Beetz, Jenn McArthur
Publisher	European Council on Computing in Construction (EC3)
ISBN (Print)	9789083451312
DOIs	https://doi.org/10.35490/EC3.2025.235
Publication status	Published - Jul 2025
Event	European Conference on Computing in Construction, EC3 2025 and 42nd International CIB W78 Conference on IT in Construction, 2025 - Porto, Portugal Duration: 14 Jul 2025 → 17 Jul 2025

Publication series

Name	Proceedings of the European Conference on Computing in Construction
ISSN (Electronic)	2684-1150

Conference

Conference	European Conference on Computing in Construction, EC3 2025 and 42nd International CIB W78 Conference on IT in Construction, 2025
Country/Territory	Portugal
City	Porto
Period	14/07/25 → 17/07/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Building performance evaluation
Early design stage
House plan
Surrogate model
XGBoost

ASJC Scopus subject areas

Information Systems
Building and Construction

More information

10.35490/EC3.2025.235

Cite this

Liu, W., Wu, Z., Cheng, J. C. P., Kwok, H. H. L., & Tao, X. (2025). IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE. In E. Petrova, M. Srećković, P. Meda, R. K. Soman, D. Hall, J. Beetz, & J. McArthur (Eds.), Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025 (Proceedings of the European Conference on Computing in Construction). European Council on Computing in Construction (EC3). https://doi.org/10.35490/EC3.2025.235

Liu, Wenli ; Wu, Zhaoji ; Cheng, Jack C.P. et al. / IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE. Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025. editor / Ekaterina Petrova ; Marijana Srećković ; Pedro Meda ; Ranjith K. Soman ; Daniel Hall ; Jakob Beetz ; Jenn McArthur. European Council on Computing in Construction (EC3), 2025. (Proceedings of the European Conference on Computing in Construction).

@inproceedings{8871325e1fb04a0394a3614a4672e48d,

title = "IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE",

abstract = "The performance evaluation is crucial in comparing multiple house plans during the early stages. However, simulation-based methods often face challenges such as time consumption and complex modeling processes. Therefore, this paper extracted the features from house plans and proposed an image-based algorithm for automatic geometric simulation modeling. The algorithm successfully modeled 16,000 house plans and obtained simulation results for their energy consumption, indoor thermal comfort, and daylighting. This paper further compares the MARS-based and XGBoost-based surrogate models for performance evaluation using the house plan dataset. The results indicate that XGBoost performed better on all metrics.",

keywords = "Building performance evaluation, Early design stage, House plan, Surrogate model, XGBoost",

author = "Wenli Liu and Zhaoji Wu and Cheng, \{Jack C.P.\} and Kwok, \{Helen H.L.\} and Xingyu Tao",

note = "Publisher Copyright: {\textcopyright} 2025, European Council on Computing in Construction (EC3). All rights reserved.; European Conference on Computing in Construction, EC3 2025 and 42nd International CIB W78 Conference on IT in Construction, 2025 ; Conference date: 14-07-2025 Through 17-07-2025",

year = "2025",

month = jul,

doi = "10.35490/EC3.2025.235",

language = "English",

isbn = "9789083451312",

series = "Proceedings of the European Conference on Computing in Construction",

publisher = "European Council on Computing in Construction (EC3)",

editor = "Ekaterina Petrova and Marijana Sre{\'c}kovi{\'c} and Pedro Meda and Soman, \{Ranjith K.\} and Daniel Hall and Jakob Beetz and Jenn McArthur",

booktitle = "Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025",

}

Liu, W, Wu, Z, Cheng, JCP, Kwok, HHL & Tao, X 2025, IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE. in E Petrova, M Srećković, P Meda, RK Soman, D Hall, J Beetz & J McArthur (eds), Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025. Proceedings of the European Conference on Computing in Construction, European Council on Computing in Construction (EC3), European Conference on Computing in Construction, EC3 2025 and 42nd International CIB W78 Conference on IT in Construction, 2025, Porto, Portugal, 14/07/25. https://doi.org/10.35490/EC3.2025.235

IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE. / Liu, Wenli; Wu, Zhaoji; Cheng, Jack C.P. et al.
Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025. ed. / Ekaterina Petrova; Marijana Srećković; Pedro Meda; Ranjith K. Soman; Daniel Hall; Jakob Beetz; Jenn McArthur. European Council on Computing in Construction (EC3), 2025. (Proceedings of the European Conference on Computing in Construction).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE

AU - Liu, Wenli

AU - Wu, Zhaoji

AU - Cheng, Jack C.P.

AU - Kwok, Helen H.L.

AU - Tao, Xingyu

PY - 2025/7

Y1 - 2025/7

N2 - The performance evaluation is crucial in comparing multiple house plans during the early stages. However, simulation-based methods often face challenges such as time consumption and complex modeling processes. Therefore, this paper extracted the features from house plans and proposed an image-based algorithm for automatic geometric simulation modeling. The algorithm successfully modeled 16,000 house plans and obtained simulation results for their energy consumption, indoor thermal comfort, and daylighting. This paper further compares the MARS-based and XGBoost-based surrogate models for performance evaluation using the house plan dataset. The results indicate that XGBoost performed better on all metrics.

AB - The performance evaluation is crucial in comparing multiple house plans during the early stages. However, simulation-based methods often face challenges such as time consumption and complex modeling processes. Therefore, this paper extracted the features from house plans and proposed an image-based algorithm for automatic geometric simulation modeling. The algorithm successfully modeled 16,000 house plans and obtained simulation results for their energy consumption, indoor thermal comfort, and daylighting. This paper further compares the MARS-based and XGBoost-based surrogate models for performance evaluation using the house plan dataset. The results indicate that XGBoost performed better on all metrics.

KW - Building performance evaluation

KW - Early design stage

KW - House plan

KW - Surrogate model

KW - XGBoost

UR - https://www.scopus.com/pages/publications/105029441638

U2 - 10.35490/EC3.2025.235

DO - 10.35490/EC3.2025.235

M3 - Conference article published in proceeding or book

AN - SCOPUS:105029441638

SN - 9789083451312

T3 - Proceedings of the European Conference on Computing in Construction

BT - Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025

A2 - Petrova, Ekaterina

A2 - Srećković, Marijana

A2 - Meda, Pedro

A2 - Soman, Ranjith K.

A2 - Hall, Daniel

A2 - Beetz, Jakob

A2 - McArthur, Jenn

PB - European Council on Computing in Construction (EC3)

T2 - European Conference on Computing in Construction, EC3 2025 and 42nd International CIB W78 Conference on IT in Construction, 2025

Y2 - 14 July 2025 through 17 July 2025

ER -

Liu W, Wu Z, Cheng JCP, Kwok HHL, Tao X. IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE. In Petrova E, Srećković M, Meda P, Soman RK, Hall D, Beetz J, McArthur J, editors, Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025. European Council on Computing in Construction (EC3). 2025. (Proceedings of the European Conference on Computing in Construction). doi: 10.35490/EC3.2025.235

IMAGE-BASED AUTOMATIC MODELING AND PERFORMANCE EVALUATION FOR HOUSE PLANS IN THE EARLY DESIGN STAGE

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this