StylePeople

Home Abstract Code Video

 
      StylePeople
      StylePeople
      StylePeople
      
      A Generative Model of Fullbody Human Avatars
      A Generative Model of Fullbody Human Avatars
      A Generative Model of Fullbody Human Avatars

 
      Artur Grigorev*
      Artur Grigorev*
      Artur Grigorev*
    
      Karim Iskakov*
      Karim Iskakov*
      Karim Iskakov*
    
      Anastasia Ianina
      Anastasia Ianina
      Anastasia Ianina
    
      Renat Bashirov
      Renat Bashirov
      Renat Bashirov

 
      Ilya Zakharkin
      Ilya Zakharkin
      Ilya Zakharkin
    
      Alexander Vakhitov
      Alexander Vakhitov
      Alexander Vakhitov
    
      Victor Lempitsky
      Victor Lempitsky
      Victor Lempitsky

 
        Figure 1: Style people, i.e. random samples from our generative models of human avatars. Each avatar is shown from two different viewpoints. The samples show diversity in terms of clothing and demographics. Loose clothing and hair are present.

 
ArXiv

 
      Code

 
        This project consists of two parts. The first part, named Neural Textures shows textures optimized over a video of single person via backpropogation. The second one, StylePeole presents a generative model able to sample random neural textures as well as optimize latent code in one-shot or few-shot mode.

 
Neural Textures repository

StylePeople repository

 
      Abstract

 
        We propose a new type of full-body human avatars, which combines parametric mesh-based body model with a neural texture. We show that with the help of neural textures, such avatars can successfully model clothing and hair, which usually poses a problem for mesh-based approaches. We also show how these avatars can be created from multiple frames of a video using backpropagation. We then propose a generative model for such avatars that can be trained from datasets of images and videos of people. The generative model allows us to sample random avatars as well as to create dressed avatars of people from one or few images.

 
        Figure 2: Our generative architecture is based on the combination of StyleGANv2 and Neural dressing. The StyleGAN part is used to generate neural textures, which are then superimposed on SMPL-X meshes and rendered with a neural renderer. During adversarial learning, the discriminator considers a pair of images of the same person.

 
      Data

For this project we used two novel dataset: TEDXPeople. You may find the link to the dataset page below:

 
TEDXPeople

 
      Video