# Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

## TL;DR

This paper introduces a few-shot adversarial learning system capable of quickly creating highly realistic and personalized neural talking head models from minimal images, including paintings, by leveraging meta-learning and high-capacity generative adversarial networks.

## Contribution

It presents a novel few-shot learning approach that initializes generator and discriminator parameters for personalized neural talking head models using meta-learning, enabling rapid training from limited data.

## Key findings

- Successfully generates realistic talking head models from a single image.
- Achieves rapid training by person-specific parameter initialization.
- Extends to portrait paintings, demonstrating versatility.

## Abstract

Several recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head model, these works require training on a large dataset of images of a single person. However, in many practical scenarios, such personalized talking head models need to be learned from a few image views of a person, potentially even a single image. Here, we present a system with such few-shot capability. It performs lengthy meta-learning on a large dataset of videos, and after that is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators. Crucially, the system is able to initialize the parameters of both the generator and the discriminator in a person-specific way, so that training can be based on just a few images and done quickly, despite the need to tune tens of millions of parameters. We show that such an approach is able to learn highly realistic and personalized talking head models of new people and even portrait paintings.