Disentangled Face Identity Representations for joint 3D Face Recognition and Expression Neutralisation
This addresses the challenge of accurate 3D face recognition in the presence of expressions, which is incremental as it builds on existing disentanglement and GAN methods.
The paper tackles the problem of disentangling identity from expression in 3D faces, proposing a deep learning approach that extracts identity representations and neutralizes expressions, achieving effective results on three public datasets.
In this paper, we propose a new deep learning-based approach for disentangling face identity representations from expressive 3D faces. Given a 3D face, our approach not only extracts a disentangled identity representation but also generates a realistic 3D face with a neutral expression while predicting its identity. The proposed network consists of three components; (1) a Graph Convolutional Autoencoder (GCA) to encode the 3D faces into latent representations, (2) a Generative Adversarial Network (GAN) that translates the latent representations of expressive faces into those of neutral faces, (3) and an identity recognition sub-network taking advantage of the neutralized latent representations for 3D face recognition. The whole network is trained in an end-to-end manner. Experiments are conducted on three publicly available datasets showing the effectiveness of the proposed approach.