Eyelid Fold Consistency in Facial Modeling

TL;DR

This paper introduces a new approach to model eyelid shapes consistently across diverse individuals, improving facial modeling accuracy and machine learning performance.

Contribution

A novel definition of eyelid fold consistency and geometric processing techniques for unified eyelid shape modeling across diverse faces.

Findings

Enhanced facial modeling fidelity

Improved machine learning task performance

Better representation of eyelid diversity

Abstract

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.