Plausible 3D Face Wrinkle Generation Using Variational Autoencoders

Qixin Deng , Luming Ma, Luming Ma, Aobo Jin, Huikun Bi, Binh Huy Le, and Zhigang Deng

IEEE Transactions on Visualization and Computer Graphics 2021

Our network architecture overview. Our VAE consists of an encoder and a decoder, the encoder takes wrinkle tensors as inputs, and the
decoder is able to generate wrinkle tensors. Our wrinkle embedding network aims to sample the latent space z, therefore, the decoder of the VAE
can produce corresponding wrinkle tensors.


Abstract: Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolved. In this paper we propose an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. We also introduce a complete pipeline to transfer the synthesized wrinkles between faces with different shapes and topologies. Through many experiments, we demonstrate our method can robustly synthesize plausible fine-scale wrinkles on a variety of coarse-scale 3D faces with different shapes and expressions.


Download: [paper] [video]


Demo Video on Youtube