StylePeople: A Generative Model of Fullbody Human Avatars

TL;DR

This paper introduces StylePeople, a generative model for full-body human avatars that combines parametric meshes with neural textures, enabling realistic clothing and hair modeling from images or videos.

Contribution

It presents a novel generative model that creates detailed, dressed human avatars from limited input data, integrating mesh models with neural textures.

Findings

Successfully models clothing and hair with neural textures

Can generate avatars from single or few images

Supports sampling diverse and dressed avatars

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. The code for the project is available at saic-violet.github.io/style-people.