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

StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

Kwan Yun, Changmin Lee, AYeong Jeong, Youngseo Kim, Seungmi Lee, Junyong Noh

ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-17

DOI: 10.1145/3811360 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Kwan Yun und 5 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable identity. However, current identity encoders, which are typically trained and calibrated on natural photographs, exhibit severe brittleness under stylization. They often mistake changes in texture or color palette for identity drift or fail to detect geometric exaggerations. This reveals the lack of a style-agnostic framework to evaluate and supervise identity consistency across varying styles and strengths. To address this gap, we introduce StyleID, a human perception-aware dataset and evaluation framework for facial identity under stylization. StyleID comprises two datasets: (i) StyleBench-H, a benchmark that captures human same-different verification judgments across diffusion- and flow-matching-based stylization at multiple style strengths, and (ii) StyleBench-S, a supervision set derived from psychometric recognition-strength curves obtained through controlled two-alternative forced-choice (2AFC) experiments. Leveraging StyleBench-S, we fine-tune existing semantic encoders to align their similarity orderings with human perception across styles and strengths. Experiments demonstrate that our calibrated models yield significantly higher correlation with human judgments and enhanced robustness for out-of-domain, artist drawn portraits. All of our datasets, code, and pretrained models will be publicly available.

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation

Zitieren

APA

Yun, K., Lee, C., Jeong, A., Kim, Y., Lee, S., & Noh, J. (2026). StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition. ACM Transactions on Graphics, 45(4), 1-17. https://doi.org/10.1145/3811360

Vancouver

Yun K, Lee C, Jeong A, Kim Y, Lee S, Noh J. StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition. ACM Transactions on Graphics. 2026;45(4):1-17. doi:10.1145/3811360

BibTeX
@article{Yun2026,
  author = {Yun, Kwan and Lee, Changmin and Jeong, AYeong and Kim, Youngseo and Lee, Seungmi and Noh, Junyong},
  title = {StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {4},
  pages = {1--17},
  doi = {10.1145/3811360}
}
Kostenlos starten →