A 3D model-based approach for fitting masks to faces in the wild

TL;DR

This paper introduces WearMask3D, a 3D model-based method for generating realistic masked face images in various poses to improve face recognition accuracy during the COVID-19 pandemic.

Contribution

We propose a novel 3D model-based approach for realistic masked face augmentation, enabling better training data for face recognition systems in masked scenarios.

Findings

WearMask3D produces more realistic masked faces.

Augmentation with WearMask3D improves recognition accuracy.

The method effectively handles diverse poses and lighting conditions.

Abstract

Face recognition now requires a large number of labelled masked face images in the era of this unprecedented COVID-19 pandemic. Unfortunately, the rapid spread of the virus has left us little time to prepare for such dataset in the wild. To circumvent this issue, we present a 3D model-based approach called WearMask3D for augmenting face images of various poses to the masked face counterparts. Our method proceeds by first fitting a 3D morphable model on the input image, second overlaying the mask surface onto the face model and warping the respective mask texture, and last projecting the 3D mask back to 2D. The mask texture is adapted based on the brightness and resolution of the input image. By working in 3D, our method can produce more natural masked faces of diverse poses from a single mask texture. To compare precisely between different augmentation approaches, we have constructed a dataset comprising masked and unmasked faces with labels called MFW-mini. Experimental results demonstrate WearMask3D produces more realistic masked faces, and utilizing these images for training leads to state-of-the-art recognition accuracy for masked faces.