M-StruGAN - An Automatic 2D-Plan Generation System under Mixed Structural Constraints for Homestays

Oct 24, 2026

Existing methods for generating 2D plans with intelligent systems often rely on human-defined rules, involve complex operations, and limit scalability. GANs offer a learning-based alternative, yet it remains unclear whether single-constraint generative design can satisfy many heterogeneous constraints. This paper proposes M-StruGAN, a GAN-based structural generative model for homestay 2D-plan layout under hybrid structural constraints, verified via image synthesis quality, scheme rationality, and design quality evaluations. Results show qualified outputs, designer acceptance, and improved image fidelity and efficiency, with lower cost and more stable quality versus traditional methods.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction

Background and motivation

Related work

Rule-based, multiagent, evolutionary, and mathematical programming approaches

Article M-StruGAN: An Automatic 2D-Plan Generation System under Mixed Structural Constraints for Homestays Xiaoni Gao 1, Xiangmin Guo 1 and Tiantian Lo 2,* 1 Harbin Institute of Technology, Shenzhen 515100, China; [hathaway886@gmail.com](hathaway886@gmail.com) (X.G.); [xiangminguo@hit.edu.cn](xiangminguo@hit.edu.cn) (X.G.) 2 School of Design, Jockey Club Innovation Tower V1002e, The Hong Kong Polytechnic University, Hunghom 999077, Hong Kong * [Correspondence: 92lo@polyu.edu.hk](Correspondence: 92lo@polyu.edu.hk) Citation: Gao, X.; Guo, X.; Lo, T. M-StruGAN: An Automatic 2D-Plan Generation System under Mixed Structural Constraints for Homestays. Sustainability 2023, 15, [7126. h9ps://doi.org/10.3390/](7126. h9ps://doi.org/10.3390/)[ ](7126. h9ps://doi.org/10.3390/)su15097126 Academic Editors: Tin-Chih Toly Chen and Ali Bahadori-Jahromi Received: 21 March 2023 Revised: 21 April 2023 Accepted: 21 April 2023 Published: 24 April 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, SwiMerland. This article is an open access article distributed under the terms and conditions of the Creative Commons A9ribution (CC BY) license ([h9ps://creativecommons.org/license](h9ps://creativecommons.org/license)[s/by/4.0/](s/by/4.0/)) . Abstract: Existing methods for generating 2D plans based on intelligent systems usually require human-deﬁned rules, and their operations are complex. GANs can solve these problems through independent research and learning. However, they only have generative design research based on a single constraint condition, and whether they can generate a qualiﬁed design scheme under many constraints is still unclear. Therefore, this paper develops the M-StruGAN generative model based on the structural design framework of a GAN. Its application research is extended to the 2D-plan layout generation of homestay based on the constraints of hybrid structures, and the feasibility of the method is comprehensively veriﬁed through three aspects: image synthesis quality assessment, scheme rationality assessment, and scheme design quality assessment. Experimental results show that the quality of the drawings generated by M-StruGAN is qualiﬁed, designers have a high degree of acceptance of the design results of M-StruGAN, and M-StruGAN completed the learning of the critical points of the 2D layout. Finally, through the human–computer interaction application of MStruGAN, it can be found that compared with traditional design methods, M-StruGAN based on pix2pixHD has high-deﬁnition image quality, higher design eﬃciency, lower design cost, and more stable design quality. Keywords: homestay; 2D-plan; machine learning; GAN; Pix2pixHD 1. Introduction Since the 20th century, with the acceleration of urbanization, the transformation and utilization of old buildings has a9racted more and more a9ention from all walks of life [1]. Reusing existing buildings not only realizes the sustainable development of buildings but also eﬀectively reduces the carbon emissions of buildings [2]. During the renovation of a building, the 2D-plan layout is part of the core content of the scheme design of the building [3] . A reasonable functional layout that satisﬁes the space size, quantity, connection, and other relationships of the house to the greatest extent can bring comfort to people’s daily lives [4] . The emergence of mass tourism has brought opportunities for the development of homestays. At the same time, it has also put forward high requirements for the design of the 2D-plan layout of homestays [5] . The 2D-plan layout of a homestay is a long and tedious task in the traditional design process, especially when it comes to complex structural constraints, which require designers to repeatedly try and modify the design process, which consumes a lot of time and energy [6,7] . The design of a 2D-plan layout mainly faces the following problems: (1) The scheme design takes a longtime and needs to be revised repeatedly. (2

FAQs

Why are traditional methods for homestay 2D-plan layout difficult to use in practice?

Traditional design is time-consuming, requires repeated revisions, can be costly, and demands specialized professional knowledge from designers.

What problem does M-StruGAN aim to address?

M-StruGAN targets automatic generation of homestay 2D-plan layouts under mixed structural constraints, reducing complexity compared with rule-based approaches.

How is the feasibility of M-StruGAN verified in the study?

Feasibility is comprehensively verified through three aspects: image synthesis quality assessment, scheme rationality assessment, and scheme design quality assessment.

Oct 24, 2026

Upload by AditGamingID