papers AI Learner
The Github is limit! Click to go to the new site.

MeshGAN: Non-linear 3D Morphable Models of Faces

2019-03-25
Shiyang Cheng, Michael Bronstein, Yuxiang Zhou, Irene Kotsia, Maja Pantic, Stefanos Zafeiriou

Abstract

Generative Adversarial Networks (GANs) are currently the method of choice for generating visual data. Certain GAN architectures and training methods have demonstrated exceptional performance in generating realistic synthetic images (in particular, of human faces). However, for 3D object, GANs still fall short of the success they have had with images. One of the reasons is due to the fact that so far GANs have been applied as 3D convolutional architectures to discrete volumetric representations of 3D objects. In this paper, we propose the first intrinsic GANs architecture operating directly on 3D meshes (named as MeshGAN). Both quantitative and qualitative results are provided to show that MeshGAN can be used to generate high-fidelity 3D face with rich identities and expressions.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.10384

PDF

http://arxiv.org/pdf/1903.10384


Similar Posts

Comments