Publications

Detailed Information

A 3D MODEL-BASED APPROACH FOR FITTING MASKS TO FACES IN THE WILD

Cited 4 time in Web of Science Cited 12 time in Scopus
Authors

Hong, Je Hyeong; Kim, Hanjo; Kim, Minsoo; Nam, Gi Pyo; Cho, Junghyun; Ko, Hyeong-Seok; Kim, Ig-Jae

Issue Date
2021-04
Publisher
IEEE
Citation
Proceedings - International Conference on Image Processing, ICIP, pp.235-239
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(1) produces more realistic masked faces, and utilizing these images for training leads to state-of-the-art recognition accuracy for masked faces.
ISSN
1522-4880
URI
https://hdl.handle.net/10371/186260
DOI
https://doi.org/10.1109/ICIP42928.2021.9506069
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share