Synthesizing coupled 3D face modalities by trunk-branch generative adversarial networks
File(s)
Accepted version
Author(s)
Type
Conference Paper
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.
Date Issued
2020-10-07
Date Acceptance
2020-08-23
Citation
Computer Vision – ECCV 2020, 2020, 12374, pp.415-433
ISBN
9783030585259
ISSN
0302-9743
Publisher
Springer International Publishing
Start Page
415
End Page
433
Journal / Book Title
Computer Vision – ECCV 2020
Volume
12374
Copyright Statement
© 2020 Springer Nature Switzerland AG. his version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/ 10.1007/978-3-030-58526-6_25
Identifier
http://dx.doi.org/10.1007/978-3-030-58526-6_25
http://arxiv.org/abs/1909.02215v3
Source
European Conference on Computer Vision
Subjects
cs.CV
cs.CV
cs.GR
Artificial Intelligence & Image Processing
Notes
Check project page: https://github.com/barisgecer/TBGAN for the full resolution results and the accompanying video
Publication Status
Published
Start Date
2020-08-23
Finish Date
2020-08-28
Coverage Spatial
Glasgow, UK
Date Publish Online
2020-10-07