Dense 3D Face Decoding Over 2500FPS: Joint Texture and Shape Convolutional Mesh Decoders. Y Zhou, Ji Deng, I Kotsia, S Zafeiriou.
Date: June 2019.
Source: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.
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). Nevertheless, all of the above methods use either fully connected layers or 2D convolutions on parametric unwrapped UV spaces leading to large networks with many parameters. 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. …We train our method using both under-controlled data (3dMD) and in-the-wild data (300W-LP and
CelebA). The 3dMD dataset  contains around 21k raw scans of 3,564 unique identities with expression variations.
Article: Dense 3D Face Decoding Over 2500FPS: Joint Texture and Shape Convolutional Mesh Decoders.
Authors: Yuxiang Zhou, Jiankang Deng, Irene Kotsia, Stefanos Zafeiriou. Imperial College London, UK.