Style mixing houses
The role of high- and low-level visual features in human house facade evaluation
Bibliographic Data
| ID | 9406754 |
|---|---|
| Authors | Kira Pohlmann (0009-0002-7971-8631, Max Planck Institute for Human Development, corresponding author), Nour Tawil (0000-0002-1346-0917, Max Planck Institute for Human Development), Timothy R Brick (0000-0002-3339-9279, Pennsylvania State University), Simone Kühn (Universität Hamburg) |
| Year | 2025 |
| Volume | 262 |
| Pages | 106126-106126 |
| Publication date | 2025-12-19 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Acta Psychologica (JOURNAL) |
| Journal identifiers | ISSN: 0001-6918 • E-ISSN: 1873-6297 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.actpsy.2025.106126 |
| PMID | 41421111 |
| OpenAlex | W7116112128 |
| Language | EN |
| References cited | 43 |
The influence of architectural design on well-being is increasingly recognised, underscoring the need to understand how humans evaluate their surroundings. This study examines the impact of low-level visual features and high-level architectural elements in images of house facades generated by a generative adversarial network (GAN). We introduce a novel method to create controlled image datasets using the style mixing component of StyleGAN2-ADA, enabling the combination of specific architectural features with styles representing low-level image properties, such as brightness or colour. Our dataset consists of 900 images encompassing five high-level features (house size, garage door visibility, number of windows, entrance door visibility, and roof shape) and 16 low-level visual features. These GAN-generated images were rated in an online experiment by 303 participants on six dimensions: facelikeness, hominess, relaxation, invitingness, safety, and price. Linear mixed-effects models identified significant predictors, including the number of floors as a high-level feature and green pixel percentage, saturation (SD), brightness (SD), and contrast as low-level features. This indicated that houses with two floors and images with an overall higher amount of green pixel, as well as diversity of saturation and brightness and a lower contrast were rated as, e.g., more inviting and safer. The analysis showed that high- and low-level features explained up to 54 % of the variance in house price ratings, with high-level features accounting for the larger share and highlighting their relevance for house facade evaluations. This work advances the use of GANs and offers a method to modify visual elements that shape architectural evaluations
Architectural style · Brightness · Contrast (vision · Facade · Feature (linguistics · Generative grammar · Image (mathematics · Matching (statistics · Pixel · Architecture, Modernity, and Design · Cultural Heritage Management and Preservation · Urban Design and Spatial Analysis
The National Human Activity Pattern Survey (NHAPS)
A Computational Approach to Edge Detection
oTree—An open-source platform for laboratory, online, and field experiments
Who Sees Human?
Environmental preference and restoration
Feature Selection with the Boruta Package
Regression Shrinkage and Selection Via the Lasso
The Vienna Art Interest and Art Knowledge Questionnaire (Vaiak)
Order, complexity, and aesthetic preferences for neatly organized compositions
Do you see the “face”? Individual differences in face pareidolia
Low-Level Visual Features of Window Views Contribute to Perceived Naturalness and Mental Health Outcomes
The restorative benefits of nature
| Highly cited | No |
|---|