# Unsupervised Creation of Parameterized Avatars

arXiv: https://arxiv.org/abs/1704.05693 · HTML: https://mlsanity.com/paper/1704.05693/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2017.

## Built on by (most cited first, 6 of 6)

- [Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation](https://mlsanity.com/paper/2303.01311/) (2023)
- [Bring Your Own Character: A Holistic Solution for Automatic Facial Animation Generation of Customized Characters](https://mlsanity.com/paper/2402.13724/) (2024)
- [SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines](https://mlsanity.com/paper/2301.08153/) (2023)
- [Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers](https://mlsanity.com/paper/2205.06305/) (2022)
- [Biometrics in Extended Reality: A Review](https://mlsanity.com/paper/2411.10489/) (2024)
- [Unsupervised Cross-Domain Regression for Fine-grained 3D Game Character Reconstruction](https://mlsanity.com/paper/2412.10430/) (2024)

## Abstract (arXiv)

We study the problem of mapping an input image to a tied pair consisting of a vector of parameters and an image that is created using a graphical engine from the vector of parameters. The mapping's objective is to have the output image as similar as possible to the input image. During training, no supervision is given in the form of matching inputs and outputs. This learning problem extends two literature problems: unsupervised domain adaptation and cross domain transfer. We define a generalization bound that is based on discrepancy, and employ a GAN to implement a network solution that corresponds to this bound. Experimentally, our method is shown to solve the problem of automatically creating avatars.