3D face representation and reconstruction with multi-scale graph convolutional autoencoders

Yuan, Cunkuan, Li, Kun, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Yang, Jingyu 2019. 3D face representation and reconstruction with multi-scale graph convolutional autoencoders. Presented at: IIEEE International Conference on Multimedia and Expo (ICME) 2019, Shanghai, China, 8-12 July 2019. 2019 IEEE International Conference on Multimedia and Expo (ICME). 2025 IEEE International Conference on Multimedia and Expo (ICME). IEEE, pp. 1558-1563. 10.1109/ICME.2019.00269

Preview

PDF - Accepted Post-Print Version Download (2MB) | Preview

Abstract

Effective representation and reconstruction for human faces are very important in many applications. Existing linear representation methods cannot reconstruct high quality 3D faces with details, while the newest non-linear representation method is less suitable for real shapes since spectral decompositions are unstable across different graphs. To address these problems, we propose a multi-scale graph convolutional autoencoder for face representation and reconstruction. Our autoencoder uses graph convolution, which is easily trained for the data with graph structures and can be used for other deformable models. Our model can also be used for variational training to generate high quality face shapes. Experimental results demonstrate that our model can generate more plausible, complex, and stable 3D shapes, and achieves higher quality face reconstruction compared with state-of-the-art methods.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	978-1-5386-9553-1
ISSN:	1945-7871
Related URLs:	Organisation
Date of First Compliant Deposit:	5 April 2019
Last Modified:	23 Jun 2026 10:34
URI:	https://orca.cardiff.ac.uk/id/eprint/121528

Actions (repository staff only)

Edit Item