Dense 3D face decoding over 2500FPS: Joint texture and shape convolutional mesh decoders

Zhou, Yuxiang, Deng, Jiankang, Kotsia, Irene and Zafeiriou, Stefanos (2019) Dense 3D face decoding over 2500FPS: Joint texture and shape convolutional mesh decoders. In: International Conference on Computer Vision and Pattern Recognition, 16-20 Jun 2019, Long Beach, California. (Published online first)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (8MB) | Preview

Abstract

3D Morphable Models (3DMMs) are statistical models that represent facial texture and shape variations using a set of linear bases and more particular Principal Component Analysis (PCA). 3DMMs were used as statistical priors for reconstructing 3D faces from images by solving non-linear least square optimization problems. Recently, 3DMMs were used as generative models for training non-linear mappings (i.e., regressors) from image to the parameters of the models via Deep Convolutional Neural Networks (DCNNs). Nev- ertheless, all of the above methods use either fully con- nected layers or 2D convolutions on parametric unwrapped UV spaces leading to large networks with many parame- ters. In this paper, we present the first, to the best of our knowledge, non-linear 3DMMs by learning joint texture and shape auto-encoders using direct mesh convolutions. We demonstrate how these auto-encoders can be used to train very light-weight models that perform Coloured Mesh Decoding (CMD) in-the-wild at a speed of over 2500 FPS.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 26524
Notes on copyright: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Useful Links:
Depositing User: Irene Kotsia
Date Deposited: 02 May 2019 08:21
Last Modified: 27 Jun 2019 16:38
URI: https://eprints.mdx.ac.uk/id/eprint/26524

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year