Quantifying Structural Divergence Between Human and Diffusion-Based Generative Visual Compositions
Applied Sciences · 09.04.2026 · 16 (8) · 3669
DOI: 10.3390/app16083669 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 09.04.2026. Verfasst von Necati Vardar und 1 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid proliferation of text-to-image generative systems has transformed visual content production, yet the structural characteristics embedded in their compositional outputs remain insufficiently understood. Rather than approaching human–AI differentiation as a purely classification problem, this study investigates whether a controlled set of AI-generated and human-designed posters exhibits measurable structural divergence under thematically matched conditions. A dataset of jazz festival posters was analyzed using interpretable geometric and information-theoretic descriptors, including spatial density (padding ratio), edge density, chromatic dispersion, and entropy-based measures. Instead of relying on deep neural detection architectures, we employed a transparent machine-learning framework to examine intrinsic structural separability within feature space. Results demonstrated highly stable group separation (ROC-AUC = 0.99; 95% CI: 0.978–0.999) under cross-validated evaluation. Distributional analysis further revealed a pronounced divergence in spatial density allocation (Kolmogorov–Smirnov statistic = 0.76, p < 10−28), accompanied by a very large effect size (Cohen’s d = 1.365). While padding ratio emerged as the dominant discriminative factor, additional entropy- and chromatic-based descriptors contributed to group separation even when spatial density was excluded (AUC = 0.903). These findings indicate that AI-generated and human-designed posters can diverge in negative space allocation and chromatic organization under controlled thematic and platform-specific conditions. The study contributes to the explainable analysis of generative visual systems by reframing human–AI differentiation as a structural divergence problem grounded in interpretable image statistics rather than as a model-specific artifact detection task.
Zitieren
APA
Vardar, N., & Gümüş, Ç. (2026). Quantifying Structural Divergence Between Human and Diffusion-Based Generative Visual Compositions. Applied Sciences, 16(8), 3669. https://doi.org/10.3390/app16083669
Vancouver
Vardar N, Gümüş Ç. Quantifying Structural Divergence Between Human and Diffusion-Based Generative Visual Compositions. Applied Sciences. 2026;16(8):3669. doi:10.3390/app16083669
BibTeX
@article{Vardar2026,
author = {Vardar, Necati and Gümüş, Çağrı},
title = {Quantifying Structural Divergence Between Human and Diffusion-Based Generative Visual Compositions},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {8},
pages = {3669},
doi = {10.3390/app16083669}
}
EUVIMED