Generating 3D faces using Convolutional Mesh Autoencoders

TL;DR

This paper introduces a non-linear spectral mesh autoencoder for 3D face generation, capturing complex deformations and expressions more effectively than linear models, with improved accuracy and efficiency.

Contribution

It presents a novel spectral convolution-based autoencoder that models non-linear face variations hierarchically, outperforming existing models with fewer parameters and lower error.

Findings

Outperforms state-of-the-art face models with 50% lower error

Uses 75% fewer parameters than previous models

Successfully captures extreme expressions and non-linear deformations

Abstract

Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation. Traditional models learn a latent representation of a face using linear subspaces or higher-order tensor generalizations. Due to this linearity, they can not capture extreme deformations and non-linear expressions. To address this, we introduce a versatile model that learns a non-linear representation of a face using spectral convolutions on a mesh surface. We introduce mesh sampling operations that enable a hierarchical mesh representation that captures non-linear variations in shape and expression at multiple scales within the model. In a variational setting, our model samples diverse realistic 3D faces from a multivariate Gaussian distribution. Our training data consists of 20,466 meshes of extreme expressions captured over 12 different subjects. Despite limited training data, our trained model outperforms state-of-the-art face models with 50% lower reconstruction error, while using 75% fewer parameters. We also show that, replacing the expression space of an existing state-of-the-art face model with our autoencoder, achieves a lower reconstruction error. Our data, model and code are available at http://github.com/anuragranj/coma