AccScience Publishing / IJOCTA / Online First / DOI: 10.36922/IJOCTA025350148
Submit to IJOCTA
Cite this article
13
Download
98
Views
Journal Browser
Volume | Year
Issue
Search
Forthcoming Issue
Current Issue
View All
News and Announcements
View All
RESEARCH ARTICLE

A StyleGAN2-based framework for generating and evaluating urban color landscapes and street vitality

Jijiang Zhang1 ,  Faziawati Abdul Aziz1* ,  Mohd Fabian Hasna1
Show Less
1 Department of Landscape Architecture, Faculty of Design and Architecture, Universiti Putra Malaysia, Serdang, Selangor Darul Ehsan, Malaysia
IJOCTA, 025350148 https://doi.org/10.36922/IJOCTA025350148
Received: 27 August 2025 | Revised: 20 November 2025 | Accepted: 21 November 2025 | Published online: 7 January 2026
© 2026 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Download PDF
XML
Cite
Abstract

Urban color landscapes play a significant role in shaping perceptual experience and street vitality. We proposed a style-based generative adversarial network 2 (StyleGAN2)-inspired generative framework for creating urban colorscapes and quantitatively assessing their vitality. The approach integrated advanced data preprocessing, generator–discriminator architecture, and hyperparameter optimization using a non-saturating logistic loss function. Vitality was evaluated through three chromatic indicators—saturation, contrast, and diversity—and validated against behavioral (pedestrian volume) and socioeconomic (point of-interest density) data via correlation analysis (r = 0.47–0.68). The model achieved theoretical convergence (Fréchet Inception Distance < 15) and optimality, while ablation experiments with a deep convolutional GAN, Wasserstein GAN with gradient penalty, and StyleGAN3 confirmed its superior generative performance. The synthesized images exhibited an 18.2% increase in saturation and a 10.5% increase in diversity relative to real-world scenes, suggesting a strong positive association with urban vitality, as established in our correlation analysis. Computational efficiency was enhanced through mixed precision training, reducing total processing time. Empirical and perceptual validations confirmed the framework’s robustness, offering a reproducible pathway for artificial intelligence-driven urban color planning.

Graphical abstract
Keywords
Adversarial networks
StyleGAN2
Urban colorscape generative
Visual analytics
Vitality assessment
Funding
This research was supported by the Universiti Putra Malaysia Grant (Geran Putra IPS) under Grant Number GP-IPS-9772600.
Conflict of interest
The authors declare that they have no competing interests.
References
  1. Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019:4396–4405. https://doi.org/10.1109/CVPR.2019.00453

 

  1. Batty M. The New Science of Cities. Cambridge, MA, USA: MIT Press; 2017.

 

  1. Karras T, Aittala M, Hellsten J, Laine S, Lehtinen J, Aila T. Training generative adversarial networks with limited data. In: Advances in Neural Information Processing Systems. Curran Associates, 2020:12104–12114. https://papers.nips.cc/paper/2020/hash/8d30aa96e72440759f74bd2306c1fa3d-Abstract.html. Accessed November 1, 2025.

 

  1. Jacobs J. The Death and Life of Great American Cities. Vintage Books; 1961.

 

  1. Chen R, Zhao J, Yao X, et al. Enhancing urban landscape design: a GAN-based approach for rapid color rendering of park sketches. Land. 2024;13(2):254. https://doi.org/10.3390/land13020254

 

  1. Remtulla R, Samet A, Kulbay M, et al. A future picture: a review of current generative adversarial neural networks in vitreoretinal pathologies and their future potentials. Biomedicines. 2025;13(2):284. https://doi.org/10.3390/biomedicines13020284

 

  1. Farooq MA, Yao W, Costache G, Corcoran P. ChildGAN: large scale synthetic child facial data using domain adaptation in StyleGAN. IEEE Ac- cess. 2023;11:108775–108791. https://doi.org/10.1109/ACCESS.2023.3321149

 

  1. Karras T, Laine S, Aittala M, Hellsten J, Lehtinen J, Aila T. Analyzing and improving the image quality of StyleGAN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020:8107–8116. https://doi.org/10.1109/CVPR42600.2020.00813

 

  1. Gan W, Zhao Z, Wang Y, Zou Y, Zhou S, Wu Z. UDGAN: a new urban design inspiration approach driven by using generative adversarial net- works. J Comput Des Eng. 2023;11(1):305–324. https://doi.org/10.1093/jcde/qwae014

 

  1. Meng S. Exploring in the latent space of design: a method of plausible building facades images generation, properties control and model explanation base on StyleGAN2. In: Yuan PF, Chai H, Yan C, Leach N, eds. Proceedings of the 2021 Digital- FUTURES. Singapore: Springer; 2022:55–68. https://doi.org/10.1007/978-981-16-5983-66

 

  1. Jaglarz A. Perception of color in architecture and urban space. Buildings. 2023;13:2000. https://doi.org/10.3390/buildings13082000

 

  1. Zhang A, Li W, Wu J, Lin J, Chu J, Xia C. How can the urban landscape affect urban vitality at the street block level? A case study of 15 metropolises in China. Environ Plan B Urban Anal City Sci. 2021;48(5):1245–1262. https://doi.org/10.1177/2399808320924425

 

  1. Choi J, Seo K, Ashtari A, Noh J. StyleCine- GAN: landscape cinemagraph generation using a pre-trained StyleGAN. In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE; 2024:7872–7881. https://doi.org/10.1109/CVPR52733.2024.00752

 

  1. Nami P, Jahanbakhsh P, Fathalipour A. The role and heterogeneity of visual pollution on the quality of urban landscape using GIS; case study: historical garden in city of Maraqeh. Open J Geol. 2016;6:20–29. https://doi.org/10.4236/ojg.2016.61003

 

  1. Li X, Xue S, Li Z, Fang X, Zhu T, Ni C. A candy defect detection method based on Style- GAN2 and improved YOLOv7 for imbalanced data. 2024;13(20):3343. https://doi.org/10.3390/foods13203343

 

  1. Schaerf L, Alfarano A, Postma E. ColorwAI: Generative Colorways of Textiles Through GAN and Diffusion Disentanglement. 2024. https://doi.org/10.48550/arXiv.2407.11514

 

  1. Way D-L,  Lo  C-H,  Wei  Y-H,  Shih  Z-C. TwinGAN: twin generative adversarial network for Chinese landscape painting style transfer. IEEE Access. 2023;11:60844–60852. https://doi.org/10.1109/ACCESS.2023.3274666

 

  1. Deng B. Style transfer for converting images into Chinese landscape painting based on CycleGAN. Appl Comput Eng. 2024;51:53–58. https://doi.org/10.54254/2755-2721/51/20241162

 

  1. Lee M, Lee H, Hwang S, Choi M. Understanding the impact of the walking environment on pedestrian perception and comprehension of the situation. J Transp Health. 2021;23:101267. https://doi.org/10.1016/j.jth.2021.101267

 

  1. Fedorova S. GANs for Urban Design. 2021. https://doi.org/10.48550/arXiv.2105.01727

 

  1. Sun Q, Chen Y, Tao W, et al. A GAN-based approach toward architectural line drawing colorization prototyping. Vis Comput. 2022;38:1283- 1300. https://doi.org/10.1007/s00371-021-02219-x

 

  1. Tian R. Suggestive site planning with conditional GAN and urban GIS data. In: Proceedings of the 2020 DigitalFutures. Singapore: Springer; 2021:103–113. https://doi.org/10.1007/978-981-33-4400-610

 

  1. Chang K-H,  Cheng  C-Y,  Luo  J,  Murata S,  Nourbakhsh  M,  Tsuji  Building-GAN: Graph-conditioned Architectural Volumetric De- sign Generation. 2021. https://doi.org/10.48550/arXiv.2104.13316

 

  1. Sun C, Zhou Y, Han Y. Automatic generation of architecture facade for historical urban renovation using generative adversarial network. Build Environ. 2022;212:108781. https://doi.org/10.1016/j.buildenv.2022.108781

 

  1. Wu Z, Lischinski D, Shechtman E. StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation. 2020. https://doi.org/10.48550/arXiv.2011.12799

 

  1. Zhang H,  Goodfellow  I,  Metaxas  D, Odena    Self-attention  generative  adversarial  networks.  In:   Proceedings of the 36th  International  Conference  on  Ma- chine  Learning  PMLR.  2019:7354–7363. https://proceedings.mlr.press/v97/zhang19d.html. Accessed November 1, 2025.

 

  1. Sauer A, Schwarz K, Geiger A. StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets. 2022.  https://doi.org/10.48550/arXiv.2202.00273

 

  1. Xu S, Jiang H, Wang H. A generative urban form design framework based on deep convolutional GANs and landscape pattern metrics for sustain- able renewal in highly urbanized cities. Sustainability. 2025;17(10):4548. https://doi.org/10.3390/su17104548

 

  1. Zhang R, Tang X, Wu L, Wang Y, He X, Liu M. Evaluation on AI-generative emotional design approach for urban vitality spaces: a LoRA- driven framework and empirical research. Land. 2025;14(6):1300. https://doi.org/10.3390/land14061300

 

  1. Yu M, Zheng X, Qin P, Cui W, Ji Q. Urban color perception and sentiment analysis based on deep learning and street view big data. Appl Sci. 2024;14(20):9521. https://doi.org/10.3390/app14209521

 

  1. Zhang X, Han H, Qiao L, et al. Emotional-health- oriented urban design: a novel collaborative deep learning framework for real-time landscape assessment by integrating facial expression recognition and pixel-level semantic segmentation. Int J Environ Res Public Health. 2022;19(20):13308. https://doi.org/10.3390/ijerph192013308

 

  1. Zhang C, Chen Y, Dewancker BJ, et al. Emotional landscapes in urban design: analyzing color emotional responses of the elderly to com- munity outdoor spaces in Yi Jie Qu. Buildings. 2024;14(13):793. https://doi.org/10.3390/buildings14030793

 

  1. Huang J, Johanes M, Kim FC, Doumpioti C, Holz G-C. On GANs, NLP and architecture: combining human and machine intelligences for the generation and evaluation of meaningful designs. Technol Archit Des. 2021;5(2):207–224. https://doi.org/10.1080/24751448.2021.1967060

 

  1. Xu H, Omitaomu O, Sabri S, Zlatanova S, Li X, Song Y. Leveraging Generative AI for Smart City Digital Twins: a Survey on the Autonomous Generation of Data, Scenarios, 3D City Models, and Urban Designs. 2024. https://doi.org/10.48550/arXiv.2405.19464

 

  1. He M, Liang Y, Wang S, et al. Generative AI for Urban Design: a Stepwise Approach Integrating Human Expertise with Multimodal Diffusion Models. 2025. https://doi.org/10.48550/arXiv.2505.24260

 

  1. Jiang Y, Zhang Y, Liu Y, Huang Z. A re- view of urban vitality research in the Chinese world. Trans Urban Data Sci Technol. 2023;2(2–3):81–99. https://doi.org/10.1177/27541231231154705

 

  1. Wang Z, Xia N, Zhao X, Gao X, Zhuang S, Li M. Evaluating urban vitality of street blocks based on multi-source geographic big data: a case study of Shenzhen. Int J Environ Res Public Health. 2023;20(5):3821. https://doi.org/10.3390/ijerph20053821

 

  1. Tang Q, Zheng L, Chen Y, Yan L, Chen J. Artificial intelligence empowering museum space layout design: insights from China. PLoS One. 2024;19(11):e0310594. https://doi.org/10.1371/journal.pone.0310594

 

  1. Eskandar G, Farag Y, Yenamandra T, Cremers D, Guirguis K, Bin Y. Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes. 2023. https://doi.org/10.48550/arXiv.2305.09602

 

  1. Lee G, Yim J, Kim C, Kim M. StyLandGAN: a StyleGAN Based Landscape Image Synthesis Using Depth-map. 2022. https://doi.org/10.48550/ARXIV.2205.06611

 

  1. Elliot AJ, Maier MA. Color psychology: effects of perceiving color on psychological functioning in humans. Annu Rev Psychol. 2014;65(1):95–120. https://doi.org/10.1146/annurev-psych-010213- 115035

 

  1. Li C, Zhang T, Du X, Zhang Y, Xie H. Generative AI models for different steps in architectural design: a literature review. Front Archit Res. 2024;14(3):759-783. https://doi.org/10.1016/j.foar.2024.10.001

 

  1. Sauer A, Karras T, Laine S, Geiger A, Aila T. StyleGAN-T: unlocking the power of gans for fast large-scale text-to-image synthesis. In: Proceedings of the 40th International Conference on Machine Learning PMLR. 2023:30105–30118. https://proceedings.mlr.press/v202/sauer23a.html. Accessed November 1, 2025.

 

  1. Ali M, Rossi L, Bertozzi M. CoLoR-GAN: Continual Few-shot Learning with Low-Rank Adaptation in Generative Adversarial Networks. 2025. https://doi.org/10.48550/arXiv.2510.13869

 

  1. Qian B. Intelligent interior design based on BachGAN and StyleGAN2. In: EEI 2022 4th International Conference on Electronic Engineering and Informatics. 2022:1–7. https://ieeexplore.ieee.org/document/10048242. Accessed November 1, 2025.

 

  1. Wang Z,  Shen  M,  Huang    Combining eye-tracking technology and subjective evaluation to determine building facade color combinations and visual quality. Appl Sci. 2024;14(18):8227. https://doi.org/10.3390/app14188227

 

  1. Wang Z, Shen M, Huang Y. Exploring the impact of facade color elements on visual comfort in old residential buildings in Shanghai: in- sights from eye-tracking technology. Buildings. 2024;14(6):1758. https://doi.org/10.3390/buildings14061758

 

  1. Borji A. Pros and cons of GAN evaluation measures. Comput Vis Image Underst. 2019;179:41–65. https://doi.org/10.1016/j.cviu.2018.10.009

 

  1. Kynk¨a¨anniemi T, Karras T, Laine S, Lehtinen J, Aila T. Improved precision and recall metric for assessing generative models. In: Advances in Neural Information Processing Systems. Curran Associates, Inc. 2019:3927-3936. https://proceedings.neurips.cc/paper/2019/hash/ 0234c510bc6d908b28c70ff313743079-Abstract.html. Accessed November 30, 2025.

 

  1. Chong MJ, Lee H-Y, Forsyth D. StyleGAN of all Trades: Image Manipulation with only Pretrained StyleGAN. 2021. https://doi.org/10.48550/arXiv.2111.01619

 

  1. Cordts M, Omran M, Ramos S, et al. The cityscapes dataset for semantic urban scene understanding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:3213–3223. https://doi.org/10.1109/CVPR.2016.350

 

  1. V aldez P,  Mehrabian    Effects  of color on emotions. J Exp Psychol Gen. 1994;123(4):394–409. https://doi.org/10.1037/0096-3445.123.4.394

 

  1. Gao X, Xin JH. Investigation of human’s emotional responses on colors. Color Res Appl. 2006;31(5):411–417. https://doi.org/10.1002/col.20246

 

  1. Ou L, Luo MR, Woodcock A, Wright A. A study of colour emotion and colour preference. Part I: colour emotions for single colours. Color Res Appl. 2004;29(3):232–240. https://doi.org/10.1002/col.20010

 

  1. Montgomery J. Making a city: urbanity, vitality and urban design. J Urban Des. 1998;3(1):93–116. https://doi.org/10.1080/13574809808724418

 

  1. Mehta V. Evaluating public space. J Urban Des. 2014;19(1):53–88. https://doi.org/10.1080/13574809.2013.854698
Share
Back to top
An International Journal of Optimization and Control: Theories & Applications, Electronic ISSN: 2146-5703 Print ISSN: 2146-0957, Published by AccScience Publishing
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here
Accept