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 are publicly available at https://kwanyun.github.io/StyleID_page/

翻译：摘要：创意面部风格化旨在以多样的视觉语言（如卡通、素描和绘画）呈现肖像，同时保留可识别的身份信息。然而，当前的身份编码器通常基于自然照片训练和校准，在风格化条件下表现出严重的脆弱性。它们常将纹理或色调变化误判为身份漂移，或无法检测出几何夸张变形，这揭示了在跨不同风格与强度下，缺乏一种风格无关的框架来评估和监督身份一致性。为填补这一空白，我们提出StyleID——一种面向风格化面部身份的人类感知感知数据集与评估框架。StyleID包含两个数据集：(i) StyleBench-H，一个基准数据集，捕捉基于扩散和流匹配风格化方法在多种风格强度下的人类"相同-不同"验证判断； (ii) StyleBench-S，一个监督数据集，源自通过受控的二选一强制选择(2AFC)实验获得的心理测量识别强度曲线。利用StyleBench-S，我们对现有语义编码器进行微调，使其在跨风格与强度的相似性排序与人类感知对齐。实验表明，经过校准的模型与人类判断的相关性显著提高，并在域外艺术家绘制肖像上展现出更强的鲁棒性。所有数据集、代码及预训练模型均已在 https://kwanyun.github.io/StyleID_page/ 公开提供。