3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation
- PDF / 3,616,312 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 183 Views
3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation Stylianos Moschoglou1 · Stylianos Ploumpis1 · Mihalis A. Nicolaou2 · Athanasios Papaioannou1 · Stefanos Zafeiriou1 Received: 30 April 2019 / Accepted: 7 April 2020 © The Author(s) 2020
Abstract Over the past few years, Generative Adversarial Networks (GANs) have garnered increased interest among researchers in Computer Vision, with applications including, but not limited to, image generation, translation, imputation, and superresolution. Nevertheless, no GAN-based method has been proposed in the literature that can successfully represent, generate or translate 3D facial shapes (meshes). This can be primarily attributed to two facts, namely that (a) publicly available 3D face databases are scarce as well as limited in terms of sample size and variability (e.g., few subjects, little diversity in race and gender), and (b) mesh convolutions for deep networks present several challenges that are not entirely tackled in the literature, leading to operator approximations and model instability, often failing to preserve high-frequency components of the distribution. As a result, linear methods such as Principal Component Analysis (PCA) have been mainly utilized towards 3D shape analysis, despite being unable to capture non-linearities and high frequency details of the 3D face—such as eyelid and lip variations. In this work, we present 3DFaceGAN, the first GAN tailored towards modeling the distribution of 3D facial surfaces, while retaining the high frequency details of 3D face shapes. We conduct an extensive series of both qualitative and quantitative experiments, where the merits of 3DFaceGAN are clearly demonstrated against other, state-of-the-art methods in tasks such as 3D shape representation, generation, and translation. Keywords 3D · Face · GAN · Generation · Translation · Representation
1 Introduction Communicated by Jun-Yan Zhu, Hongsheng Li, Eli Shechtman, MingYu Liu, Jan Kautz, Antonio Torralba. Stylianos Moschoglou and Stylianos Ploumpis contributed equally to this work.
B
Stylianos Moschoglou [email protected] Stylianos Ploumpis [email protected] Mihalis A. Nicolaou [email protected] Athanasios Papaioannou [email protected] Stefanos Zafeiriou [email protected]
1
Department of Computing, Imperial College London, United Kingdom and Facesoft.io., London, UK
2
Computation-based Science and Technology Research Centre, The Cyprus Institute, Nicosia, Cyprus
GANs are a promising unsupervised machine learning methodology implemented by a system of two deep neural networks competing against each other in a zero-sum game framework (Goodfellow et al. 2014). GANs became immediately very popular due to their unprecedented capability in terms of implicitly modeling the distribution of visual data, thus being able to generate and synthesize novel yet realistic images and videos, by preserving high-frequency details of the data distribution and hence appearing authentic to human observers. Many
Data Loading...
