AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Recent evidence shows that AI-generated faces are now indistinguishable from human faces. However, algorithms are trained disproportionately on White faces, and thus White AI faces may appear especially realistic. In Experiment 1 ( N = 124 adults), alongside our reanalysis of previously published data, we showed that White AI faces are judged as human more often than actual human faces—a phenomenon we term AI hyperrealism. Paradoxically, people who made the most errors in this task were the most confident (a Dunning-Kruger effect). In Experiment 2 ( N = 610 adults), we used face-space theory and participant qualitative reports to identify key facial attributes that distinguish AI from human faces but were misinterpreted by participants, leading to AI hyperrealism. However, the attributes permitted high accuracy using machine learning. These findings illustrate how psychological theory can inform understanding of AI outputs and provide direction for debiasing AI algorithms, thereby promoting the ethical use of AI.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
lavaan : An R Package for Structural Equation Modeling
Rosseel, Y. (2012) · Journal of Statistical Software · doi:10.18637/jss.v048.i02 · Cited by 27,955
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1912.04958 · Cited by 6,332
Perception and the Representative Design of Psychological Experiments
Brunswik, E. (1956) · doi:10.1525/9780520350519 · Cited by 2,974
The Relationship Between Eyewitness Confidence and Identification Accuracy: A New Synthesis
Wixted, J. T., & Wells, G. L. (2017) · Psychological Science in the Public Interest · doi:10.1177/1529100616686966 · Cited by 467 · cited 2×
“These findings are incongruent with prior face perception literature (Palermo et al., 2017; Wixted & Wells, 2017) but in line with other types of judgments in which people can be highly confident but incorrect (e.g., when people are unknowingly exposed to misinformation but report it with high…”
BackgroundResultAI-synthesized faces are indistinguishable from real faces and more trustworthy
Nightingale, S. J., & Farid, H. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2120481119 · Cited by 397
Deep models of superficial face judgments
Peterson, J. C., Uddenberg, S., Griffiths, T. L., Todorov, A., & Suchow, J. W. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2115228119 · Cited by 82 · cited 1×
“Screening for artifacts mimics how real-world users screen AI faces, either as scientists (Peterson et al., 2022) or for public use (Satter, 2021), and therefore captures the type and range of stimuli that appear online.”
Background
Cited by
The power of generative marketing: Can generative AI create superhuman visual marketing content?
Hartmann, J., Exner, Y., & Domdey, S. (2025) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2024.09.002 · Cited by 229
Williamson, S. M., & Prybutok, V. (2024) · Information · doi:10.3390/info15060299 · Cited by 146
AI-generated poetry is indistinguishable from human-written poetry and is rated more favorably
Porter, B., & Machery, E. (2024) · Scientific Reports · doi:10.1038/s41598-024-76900-1 · Cited by 133
Kovács, B. (2024) · Marketing Letters · doi:10.1007/s11002-024-09729-3 · Cited by 44
“Even more than in Study 2, the results here, showing that AI-written reviews are perceived as more human than human-written reviews, indicate a situation that AI researchers term “AI hyperrealism” (Miller et al., 2023).”
ResultDeception, Discrimination, and Objectification: Ethical Issues of Female AI Agents
Borau, S. (2025) · Journal of Business Ethics · doi:10.1007/s10551-024-05754-4 · Cited by 33
“AI-generated faces, which can be used as chatbot interfaces, are now indistinguishable from human faces, and can even be perceived as more real than human ones, a phenomenon considered hyperrealism (Miller et al., 2023).”
Metadata
- Authors
- Miller, E. J., Steward, B. A., Witkower, Z., Sutherland, C. A. M., Krumhuber, E. G., & Dawel, A.
- Venue
- Psychological Science
- Publisher
- SAGE Publications
- Published
- 2023-11-13
- Volume
- 34
- Issue
- 12
- Pages
- 1390-1403
- ISSN
- 0956-7976 (ISSN-L)
- 1467-9280
- OpenAlex
- W4388631057
- Cited by
- 134
- References
- 9
- FWCI
- 18.72
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones. https://app.cochat.ai/papers/10.1177/09567976231207095
- The paper
- Miller, E. J., Steward, B. A., Witkower, Z., Sutherland, C. A. M., Krumhuber, E. G., & Dawel, A. (2023). AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones. Psychological Science. https://doi.org/10.1177/09567976231207095
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.