A Human Ear Reconstruction Autoencoder

Hao Sun, Nick Pears, Hang Dai

2021

Abstract

The ear, as an important part of the human head, has received much less attention compared to the human face in the area of computer vision. Inspired by previous work on monocular 3D face reconstruction using an autoencoder structure to achieve self-supervised learning, we aim to utilise such a framework to tackle the 3D ear reconstruction task, where more subtle and difficult curves and features are present on the 2D ear input images. Our Human Ear Reconstruction Autoencoder (HERA) system predicts 3D ear poses and shape parameters for 3D ear meshes, without any supervision to these parameters. To make our approach cover the variance for in-the-wild images, even grayscale images, we propose an in-the-wild ear colour model. The constructed end-to-end self-supervised model is then evaluated both with 2D landmark localisation performance and the appearance of the reconstructed 3D ears.

Paper Citation

in Harvard Style

Sun H., Pears N. and Dai H. (2021). A Human Ear Reconstruction Autoencoder. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 136-145. DOI: 10.5220/0010249901360145

in Bibtex Style

@conference{visapp21,
author={Hao Sun and Nick Pears and Hang Dai},
title={A Human Ear Reconstruction Autoencoder},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={136-145},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010249901360145},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - A Human Ear Reconstruction Autoencoder
SN - 978-989-758-488-6
AU - Sun H.
AU - Pears N.
AU - Dai H.
PY - 2021
SP - 136
EP - 145
DO - 10.5220/0010249901360145
PB - SciTePress