A computational framework is introduced to map aesthetic categories, highlighting distinctions between human-created competition entries and AI-generated designs. Assessment of architectural aesthetics has traditionally been subjective; however, computational methods now enable the systematic analysis and visualization of design variations. Using 14 aesthetic parameters, the framework applies Principal Component Analysis (PCA) to create visual maps of aesthetic relationships. Two hypotheses are discussed: (1) There is a hegemony of the aesthetic category of the beautiful in mainstream architectural competitions, and (2) that generative models like Stable Diffusion can produce visuals belonging to other aesthetic categories. The computational aesthetic framework is applied to verify both. The first hypothesis is disproven by revealing that human-created designs demonstrate significant aesthetic variation and unpredictability, while the second is confirmed by demonstrating the capacity to produce images in 16 other categories beyond the beautiful. The maps of visual relationships group images by aesthetic categories, encouraging designers to explore and enhance underpopulated areas. The computational aesthetics framework is used to analytically and quantitatively support arguments regarding architectural aesthetics.
GleickJ. The information: a history, a theory, a flood. Illustrated edition. Vintage, 2012.
2.
AndersonC. The end of theory: the data deluge makes the scientific method obsolete. Wired, 2008. https://www.wired.com/2008/06/pb-theory/ (accessed 13 March 2024).
3.
MayJ. Everything is already an image. Log2017: 9–26.
4.
RancièreJ. The future of the image. Reprint edition. Verso, 2009.
5.
YoungM. Reality modeled after images: architecture and aesthetics after the digital image. Routledge, 2021.
WoodburyR. Elements of parametric design. Illustrated edition. Taylor & Francis Ltd, 2010.
8.
GoodfellowIJPouget-AbadieJMirzaM, et al.Generative adversarial networks. Epub ahead of print 10 June 2014. DOI: 10.48550/arXiv.1406.2661.
9.
PodellDEnglishZLaceyK, et al.SDXL: improving latent diffusion models for high-resolution image synthesis. Epub ahead of print 4 July 2023. DOI: 10.48550/arXiv.2307.01952.
SardenbergVGuatelliIBeckerM. A computational framework for aesthetic preferences in architecture using computer vision and artificial neural networks. Int J Architect Comput2024; 23(1): 174–192.
24.
BhatSFBirklRWofkD, et al.ZoeDepth: zero-shot transfer by combining relative and metric depth. Epub ahead of print 23 2023. DOI: 10.48550/arXiv.2302.12288.
25.
SahyunMRV. Aesthetics and entropy: optimization of the brightness distribution. In: Human vision and electronic imaging XVII. SPIE, pp. 443–449.
26.
OstwaldMJVaughanJ. The fractal dimension of architecture. Springer International Publishing, 2016. DOI: 10.1007/978-3-319-32426-5. Epub ahead of print.
27.
NeumannLSbertMGoochB, et al.Computational aesthetics 2005 eurographics workshop on computational aesthetics in graphics, visualization and imaging Girona, Spain, 18–20 May 2005. Comput Graph Forum2006; 25: 145–146.
28.
HoenigF. Defining computational aesthetics. The Eurographics Association. DOI: 10.2312/COMPAESTH/COMPAESTH05/013-018. Epub ahead of print 2005.
29.
Vitruvius. The ten books on architecture. Harvard University Press. DOI: 10.4159/harvard.9780674435247. Epub ahead of print 1 October 2013.
30.
Concurso Centro Administrativo do Governo do Estado de São Paulo. Concurso Centro Administrativo do Governo do Estado de São Paulo. https://concursogovspnocentro.org.br/ (accessed 31 January 2025).
BirkinG. Aesthetic complexity: practice and perception in art & design. Doctoral. Nottingham Trent University, 2010. https://irep.ntu.ac.uk/id/eprint/91/ (accessed 17 January 2023).
33.
SardenbergVBeckerM. Aesthetics as a criterion: navigating solution spaces utilizing computer vision, the aesthetic measure, and artificial neural networks. In: 2023 Annual Modeling and Simulation Conference (ANNSIM), pp. 496–507. IEEE.
34.
VaughanJOstwaldM. Quantifying the changing visual experience of architecture: combining movement with visual complexity. 2014.
35.
TristmanR. Canon: historical and conceptual overview. Encyclopedia of aesthetics1998; 1: 331–334.
BirkhoffGD. Aesthetic measure. Harvard University Press, 1933.
46.
BenseM. Aesthetica. Agis-Verlag, 1965.
47.
BenseM. Einführung in die informationstheoretische Ästhetik. In: BenseM (ed). Max Bense: Ästhetik und Texttheorie: Ausgewählte Schriften in vier Bänden, Band 3. J.B. Metzler, pp. 251–417.
MolesAA. Cybernetics and the work of art. In: A little-known story about a movement, a magazine, and the computer’s arrival in art: new tendencies and bit international, 1961–1973. The MIT Press, 2011.
52.
MolesAA. Experimental aesthetics in the new consumer society. In: A little-known story about a movement, a magazine, and the computer’s arrival in art: new tendencies and bit international, 1961–1973. The MIT Press, 2011.
53.
KiemleM. Ästhetische Probleme der Architektur unter dem Aspekt der Informationsästhetik. Schnelle, 1967.
54.
ArnheimRKiemleM. Aesthetische Probleme der Architektur unter dem Aspekt der Informationsaesthetik. J Aesthet Art Critic1970; 28: 551–552.
55.
AkcayKAComputational aesthetics of low poly: [re]configuration of form. In: GomezPBraidaF (eds.), Designing possibilities - proceedings of the XXV international conference of the Ibero-American society of digital graphics (SIGraDi 2021), pp. 17–28. CUMINCAD. https://papers.cumincad.org/cgi-bin/works/paper/sigradi2021_235 (2021, accessed 24 April 2023).
56.
BhattacharyaSSukthankarRShahM. A framework for photo-quality assessment and enhancement based on visual aesthetics. In: Proceedings of the 18th ACM international conference on Multimedia, pp. 271–280. Association for Computing Machinery.
57.
BiancoSCelonaLNapoletanoP, et al.Predicting image aesthetics with deep learning. 2016.
58.
BoYYuJZhangK. Computational aesthetics and applications. Vis Comput Ind Biomed Art2018; 1: 6.
59.
DattaRJoshiDLiJ, et al.Studying aesthetics in photographic images using a computational approach. In: LeonardisABischofHPinzA (eds). Computer vision – ECCV 2006. Springer, 2006, pp. 288–301.
60.
DevKLauM. Learning perceptual aesthetics of 3-D shapes from multiple views. IEEE Comput Graph Appl2022; 42: 20–31.
61.
JinXQiaoQLuY, et al.APDDv2: aesthetics of paintings and drawings dataset with artist labeled scores and comments. Epub ahead of print 13 November 2024. DOI: 10.48550/arXiv.2411.08545.
MondolTBrownDG. Computational creativity and aesthetics with algorithmic information theory. Entropy2021; 23: 1654.
64.
ZhouYTanYLiG. Computational aesthetic measurement of photographs based on multi-features with saliency. In: HuangD-SBevilacquaVPremaratneP (eds). Intelligent computing theory. Springer International Publishing, 2014, pp. 357–366.
65.
SardenbergVBeckerM. Computational quantitative aesthetics evaluation - evaluating architectural images using computer vision, machine learning and social media. In: PakBWurzerGStouffsR (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 2, pp. 567–574. CUMINCAD. https://papers.cumincad.org/cgi-bin/works/paper/ecaade2022_75 (2022, accessed 14 December 2022).
66.
SardenbergVGuatelliIBeckerM. A walk through the latent space using computational aesthetics as a compass. In: Accelerated Landscapes: XXVII SiGraDi - Sociedad Iberoamericana de Gráfica Digital. SiGraDi, 2023. https://papers.cumincad.org/cgi-bin/works/paper/sigradi2023_80
67.
RavìFBattiatoS. A novel computational tool for aesthetic scoring of digital photography. 2012.
68.
SardenbergVBeckerM. Aesthetic measure of architectural photography utilizing computer vision: parts-from-wholes. In: Design computation input/output 2022. Design Computation. Epub ahead of print 20 October 2022. DOI: 10.47330/DCIO.2022.GGNL1577.
ZhangLRaoAAgrawalaM. Adding conditional control to text-to-image diffusion models. Epub ahead of print 26 November 2023. DOI: 10.48550/arXiv.2302.05543.
MurrayNMarchesottiLPerronninF. AVA: a large-scale database for aesthetic visual analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2408–2415. IEEE.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
