提升人脸建模中眼睑褶皱一致性，增强跨人群相似度
Eyelid Fold Consistency in Facial Modeling
- 定义眼睑褶皱一致性新标准，统一拓扑建模多样形态
- 在训练数据重处理后显著提升面部相关任务性能
- 适合需要高保真人脸建模的领域，如影视动画与数字人
眼睑形状是人物身份与相似度的关键特征。人类眼睑形态多样，个体间存在不同的皮肤褶皱和内眦褶形态差异。现有参数化人脸模型虽能表达一定眼睑变化，但难以在多样化人群中保持足够相似度。本文提出眼睑褶皱一致性的新定义，并采用几何处理技术，在统一拓扑下建模多种眼睑形状。利用该方法对参数化人脸模型的训练数据进行重处理，显著提升了相关机器学习任务的表现。
原文摘要 · Abstract (English)
Eyelid shape is integral to identity and likeness in human facial modeling. Human eyelids are diverse in appearance with varied skin fold and epicanthal fold morphology between individuals. Existing parametric face models express eyelid shape variation to an extent, but do not preserve sufficient likeness across a diverse range of individuals. We propose a new definition of eyelid fold consistency and implement geometric processing techniques to model diverse eyelid shapes in a unified topology. Using this method we reprocess data used to train a parametric face model and demonstrate significant improvements in face-related machine learning tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。