{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T15:39:09Z","timestamp":1764776349939,"version":"3.46.0"},"reference-count":42,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"ULi\u00e8ge research project \u201cDESTINA"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Text-to-image generative models can be used to imitate historical artistic styles, but their effectiveness in doing so remains unclear. In this work, we propose an evaluation framework that leverages expert knowledge from art history and visual semiotics and combines it with quantitative analysis to assess stylistic fidelity. Three experts rated both historical artwork production and images generated with Midjourney v6 for five major movements (Abstract Art, Cubism, Expressionism, Impressionism, Surrealism) and ten associated painters (male and female pairs), using nine visual criteria grounded in Greimas\u2019s plastic categories and W\u00f6lfflin\u2019s stylistic oppositions. Ratings were expressed as 95% intervals on continuous 0\u2013100 scales and compared using our Relative Ratings Map (RRMap), which summarizes relative shifts, relative dispersion, and distributional overlap (via the Bhattacharyya coefficient). They were also discretized in four quality ratings (bad, stereotype, fair, excellent). The results show strong inter-expert variability and more moderate intra-expert effects tied to movements, criteria, criterion groups and modalities. Experts tend to agree that the model sometimes aligns with historical trends but also sometimes produces stereotyped versions of a movement or painter, or even completely missed its target, although no unanimous consensus emerges. We conclude that evaluating generative models requires both expert-driven interpretation and quantitative tools, and that stylistic fidelity is hard to quantify even with a rigorous framework.<\/jats:p>","DOI":"10.3390\/jimaging11120429","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T15:02:48Z","timestamp":1764774168000},"page":"429","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["How Good Is the Machine at the Imitation Game? On Stylistic Characteristics of AI-Generated Images"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3981-6982","authenticated-orcid":false,"given":"Adrien","family":"Deli\u00e8ge","sequence":"first","affiliation":[{"name":"F.R.S.-FNRS, Rue d\u2019Egmont 5, 1000 Brussels, Belgium"},{"name":"Department of Electrical Engineering and Computer Science, Montefiore Institute, Faculty of Applied Sciences, University of Li\u00e8ge, 4000 Li\u00e8ge, Belgium"},{"name":"Department of Romance Languages and Literatures, Faculty of Philosophy and Letters, University of Li\u00e8ge, 4000 Li\u00e8ge, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8970-6048","authenticated-orcid":false,"given":"Jeanne","family":"Marlot","sequence":"additional","affiliation":[{"name":"Department of Romance Languages and Literatures, Faculty of Philosophy and Letters, University of Li\u00e8ge, 4000 Li\u00e8ge, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6260-6487","authenticated-orcid":false,"given":"Marc","family":"Van Droogenbroeck","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Montefiore Institute, Faculty of Applied Sciences, University of Li\u00e8ge, 4000 Li\u00e8ge, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2320-8130","authenticated-orcid":false,"given":"Maria Giulia","family":"Dondero","sequence":"additional","affiliation":[{"name":"F.R.S.-FNRS, Rue d\u2019Egmont 5, 1000 Brussels, Belgium"},{"name":"Department of Romance Languages and Literatures, Faculty of Philosophy and Letters, University of Li\u00e8ge, 4000 Li\u00e8ge, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"ref_1","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. (2022). Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv."},{"key":"ref_2","unstructured":"Midjourney Team (2025, September 25). Midjourney. Available online: https:\/\/www.midjourney.com."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 18\u201324). High-Resolution Image Synthesis with Latent Diffusion Models. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref_4","unstructured":"(2025, October 17). An A.I.-Generated Picture Won an Art Prize. Artists Aren\u2019t Happy. Available online: https:\/\/www.nytimes.com\/2022\/09\/02\/technology\/ai-artificial-intelligence-artists.html."},{"key":"ref_5","unstructured":"(2025, October 17). How Hollywood Writers Triumphed over AI- and Why It Matters. Available online: https:\/\/www.theguardian.com\/culture\/2023\/oct\/01\/hollywood-writers-strike-artificial-intelligence."},{"key":"ref_6","unstructured":"(2025, October 17). Tilly Norwood: How Scared Should We Be of the Viral AI \u2018Actor\u2019?. Available online: https:\/\/www.theguardian.com\/film\/2025\/sep\/30\/tilly-norwood-ai-actor-hollywood."},{"key":"ref_7","unstructured":"Saint-Germier, P., and Giavitto, J.L. (2025). L\u2019Art au Temps de l\u2019IA. G\u00e9n\u00e9rer, Critiquer, Cr\u00e9er, \u00c9ditions Centre Pompidou."},{"key":"ref_8","unstructured":"Minist\u00e8re de l\u2019\u00e9Ducation Nationale de la Jeunesse (2025). Solliciter et Questionner l\u2019Intelligence Artificielle dans le Cadre de l\u2019Enseignement des Arts Plastiques, Minist\u00e8re de l\u2019\u00c9ducation Nationale de la Jeunesse. Technical Report."},{"key":"ref_9","unstructured":"Porquet, J., Wang, S., and Chilton, L.B. (May, January 26). Copying style, Extracting value: Illustrators\u2019 Perception of AI Style Transfer and its Impact on Creative Labor. Proceedings of the CHI Conference on Human Factors in Computing Systems, Yokohama, Japan."},{"key":"ref_10","first-page":"100","article-title":"The New Value of the Archive: AI Image Generation and the Visual Economy of \u2018Style\u2019","volume":"19","author":"Meyer","year":"2023","journal-title":"IMAGE. Z. F\u00fcr Interdiszip. Bild."},{"key":"ref_11","unstructured":"Manovich, L. (2024). From Representation to Prediction: Theorizing the AI Image. Artificial Aesthetics: Generative AI, Art and Visual Media, Available online: https:\/\/www.streamingmuseum.org\/post\/manovich-artificial-aesthetics."},{"key":"ref_12","unstructured":"Dondero, M.G. (2025, October 17). Sur quelques probl\u00e8mes de composition et de style dans les mod\u00e8les d\u2019intelligence artificielle g\u00e9n\u00e9rative S\u00e9minaire international de s\u00e9miotique \u00e0 Paris, 2024\/11\/13. Available online: https:\/\/youtu.be\/I2WUdjEwD8w."},{"key":"ref_13","unstructured":"D\u2019Armenio, E., Deli\u00e8ge, A., and Dondero, M.G. (October, January 29). A Semiotic Methodology for Assessing the Compositional Effectiveness of Generative Text-to-Image Models (Midjourney and DALL\u00b7E). Proceedings of the European Conference on Computer Vision Workshops (ECCV Workshops), Milan, Italy."},{"key":"ref_14","first-page":"1","article-title":"Semiotics of Machinic Co-Enunciation","volume":"15","author":"Dondero","year":"2024","journal-title":"Signata"},{"key":"ref_15","first-page":"1","article-title":"For a Semiotic Approach to Generative Image AI: On Compositional Criteria","volume":"9","author":"Dondero","year":"2025","journal-title":"Semiot. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Deli\u00e8ge, A., Dondero, M.G., and D\u2019Armenio, E. (2025). Revisiting W\u00f6lfflin in the Age of AI: A Study of Classical and Baroque Composition in Generative Models. J. Imaging, 11.","DOI":"10.3390\/jimaging11050128"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., and Bethge, M. (2015). A Neural Algorithm of Artistic Style. arXiv.","DOI":"10.1167\/16.12.326"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., and Bethge, M. (2016, January 27\u201330). Image Style Transfer Using Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kalischek, N., Wegner, J.D., and Schindler, K. (2021, January 20\u201325). In the light of feature distributions: Moment matching for Neural Style Transfer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00926"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, Y., and Vasconcelos, N. (2021, January 20\u201325). Rethinking and Improving the Robustness of Image Style Transfer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00019"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1007\/978-3-031-16788-1_34","article-title":"ArtFID: Quantitative Evaluation of Neural Style Transfer","volume":"Volume 13485","author":"Wright","year":"2022","journal-title":"Proceedings of the DAGM German Conference on Pattern Recognition"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"10731","DOI":"10.1109\/TMM.2024.3410672","article-title":"Learning to Evaluate the Artness of AI-Generated Images","volume":"26","author":"Chen","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40494-023-01094-0","article-title":"Deep transfer learning for visual analysis and attribution of paintings by Raphael","volume":"11","author":"Ugail","year":"2023","journal-title":"Herit. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lang, S., and Ommer, B. (2018, January 8\u201314). Reflecting on How Artworks Are Processed and Analyzed by Computer Vision. Proceedings of the European Conference on Computer Vision Workshops (ECCV Workshops), Munich, Germany.","DOI":"10.1007\/978-3-030-11012-3_49"},{"key":"ref_25","unstructured":"Wan, Y., Subramonian, A., Ovalle, A., Lin, Z., Suvarna, A., Chance, C., Bansal, H., Pattichis, R., and Chang, K.W. (2024). Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Seshadri, P., Singh, S., and Elazar, Y. (2024, January 16\u201321). The Bias Amplification Paradox in Text-to-Image Generation. Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Mexico City, Mexico.","DOI":"10.18653\/v1\/2024.naacl-long.353"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Friedrich, F., Brack, M., Struppek, L., Hintersdorf, D., Schramowski, P., Luccioni, S., and Kersting, K. (2023). Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness. arXiv.","DOI":"10.1007\/s43681-024-00531-5"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"26256","DOI":"10.1609\/aaai.v39i25.34823","article-title":"Fair Text-to-Image Diffusion via Fair Mapping","volume":"Volume 39","author":"Li","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"627","DOI":"10.2307\/469358","article-title":"Figurative Semiotics and the Semiotics of the Plastic Arts","volume":"20","author":"Greimas","year":"1989","journal-title":"New Lit. Hist."},{"key":"ref_30","unstructured":"W\u00f6lfflin, H. (1915). Kunstgeschichtliche Grundbegriffe: Das Problem der Stilentwicklung in der Neueren Kunst, F. Bruckmann."},{"key":"ref_31","unstructured":"(1950). Principles of Art History: The Problem of the Development of Style in Later Art, Dover Publications, Inc."},{"key":"ref_32","unstructured":"Fontanille, J. (1995). S\u00e9miotique du Visible, Presses Universitaires de France."},{"key":"ref_33","unstructured":"Groupe \u03bc (1998). L\u2019effet de temporalit\u00e9 dans les images fixes. Texte, 41\u201369."},{"key":"ref_34","unstructured":"Basso Fossali, P., and Dondero, M.G. (2011). S\u00e9miotique de la Photographie, PULIM\u2014Universit\u00e9 de Limoges."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Lagopoulos, A.P., Boklund-Lagopoulou, K., Dondero, M.G., Fontanille, J., Katsaridou, M.I., and Walld\u00e9n, R. (2024). Semiotics of Images, De Gruyter. Semiotics, Communication and Cognition [SCC].","DOI":"10.1515\/9783110980257"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Martin, P. (2023). Le Flou et la Photographie, PRU\u2014Universit\u00e9 de Rennes.","DOI":"10.4000\/books.pur.190206"},{"key":"ref_37","unstructured":"Deleuze, G. (2003). Francis Bacon: The Logic of Sensation, Continuum Press."},{"key":"ref_38","first-page":"1","article-title":"The Experimental Space of the Diagram According to Peirce, Deleuze and Goodman: Concerning Composite Photography, Chronophotography, and Painting","volume":"9","author":"Dondero","year":"2023","journal-title":"Semiot. Rev."},{"key":"ref_39","first-page":"401","article-title":"On a Measure of Divergence between Two Multinomial Populations","volume":"7","author":"Bhattacharyya","year":"1946","journal-title":"Sankhy\u0101 Indian J. Stat."},{"key":"ref_40","first-page":"1","article-title":"Testing for equal distributions in high dimension","volume":"5","author":"Rizzo","year":"2004","journal-title":"InterStat"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1214\/09-AOAS245","article-title":"DISCO analysis: A nonparametric extension of analysis of variance","volume":"4","author":"Rizzo","year":"2010","journal-title":"Ann. Appl. Stat."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1016\/j.jspi.2013.03.018","article-title":"Energy statistics: A class of statistics based on distances","volume":"143","author":"Rizzo","year":"2013","journal-title":"J. Stat. Plan. Inference"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/12\/429\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T15:35:24Z","timestamp":1764776124000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/12\/429"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":42,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["jimaging11120429"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11120429","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]}}}