EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

AI-generated faces exhibit exaggerated facial dimorphism but lower morphological disparity than real Cameroonian faces

Olga Budnik, Karel Kleisner

Computers in Human Behavior Reports · 2026-12 · 24 · 101342

DOI: 10.1016/j.chbr.2026.101342 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers in Human Behavior Reports, 2026-12. Verfasst von Olga Budnik und 1 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Grantová Agentura České Republiky.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AI-generated faces are increasingly used as substitutes for real facial photographs in various domains of science and in practical applications, but their correspondence to natural human faces remains largely untested. We have compared real facial photographs of Cameroonian women and men with faces generated by six widely used AI models (DALL-E 3, Midjourney, Stable Diffusion, Gemini, Qwen Image, and FLUX-1). Using geometric morphometrics, we have then quantified facial morphological disparity, sexual shape dimorphism, and facial asymmetry. In all models, AI-generated faces showed substantively lower morphological disparity than real faces, which indicates a systematic compression of facial shape variation. Sexual shape dimorphism was markedly stronger in AI-generated samples than in the real population, which suggests exaggerated or unrealistic sex differentiation. Facial asymmetry did not differ between AI and real faces overall, although we did observe a small reduction in AI-generated female faces. These findings show that, despite their possible perceptual realism, AI-generated faces are not morphologically equivalent to real Cameroonian faces. The consistent reduction of facial variability and distortion of population-specific sexual dimorphism underscore the need for quantitative morphometric validation of synthetic face datasets prior to their use in scientific research or applied settings.

Förderung

  • Grantová Agentura České Republiky

Zitieren

APA

Budnik, O., & Kleisner, K. (2026). AI-generated faces exhibit exaggerated facial dimorphism but lower morphological disparity than real Cameroonian faces. Computers in Human Behavior Reports, 24, 101342. https://doi.org/10.1016/j.chbr.2026.101342

Vancouver

Budnik O, Kleisner K. AI-generated faces exhibit exaggerated facial dimorphism but lower morphological disparity than real Cameroonian faces. Computers in Human Behavior Reports. 2026;24:101342. doi:10.1016/j.chbr.2026.101342

BibTeX
@article{Budnik2026,
  author = {Budnik, Olga and Kleisner, Karel},
  title = {AI-generated faces exhibit exaggerated facial dimorphism but lower morphological disparity than real Cameroonian faces},
  journal = {Computers in Human Behavior Reports},
  year = {2026},
  volume = {24},
  pages = {101342},
  doi = {10.1016/j.chbr.2026.101342}
}
Kostenlos starten →