Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks

TL;DR

This paper introduces a novel GAN-based method that jointly generates high-quality 3D face textures, shapes, and normals, enabling photo-realistic synthesis with expression control by exploiting correlations among modalities.

Contribution

It presents the first unified GAN framework for simultaneous generation of 3D face texture, shape, and normals, advancing realistic face synthesis beyond prior separate or linear models.

Findings

Joint generation of texture, shape, and normals achieved high-quality results.

Conditional generation allows for diverse facial expressions.

Code and models are publicly available for further research.

Abstract

Generating realistic 3D faces is of high importance for computer graphics and computer vision applications. Generally, research on 3D face generation revolves around linear statistical models of the facial surface. Nevertheless, these models cannot represent faithfully either the facial texture or the normals of the face, which are very crucial for photo-realistic face synthesis. Recently, it was demonstrated that Generative Adversarial Networks (GANs) can be used for generating high-quality textures of faces. Nevertheless, the generation process either omits the geometry and normals, or independent processes are used to produce 3D shape information. In this paper, we present the first methodology that generates high-quality texture, shape, and normals jointly, which can be used for photo-realistic synthesis. To do so, we propose a novel GAN that can generate data from different modalities while exploiting their correlations. Furthermore, we demonstrate how we can condition the generation on the expression and create faces with various facial expressions. The qualitative results shown in this paper are compressed due to size limitations, full-resolution results and the accompanying video can be found in the supplementary documents. The code and models are available at the project page: https://github.com/barisgecer/TBGAN.