• Computer Science
  • Published in ArXiv 2019

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

@article{Zakharov2019FewShotAL,
  title={Few-Shot Adversarial Learning of Realistic Neural Talking Head Models},
  author={Egor Zakharov and Aliaksandra Shysheya and Egor Burkov and Victor S. Lempitsky},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.08233}
}
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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 26 CITATIONS

Improved Multi-Domain Image-to-Image Translation GAN

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Overview of Computer Vision Applications and Risks in the Global South

  • 2020
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

AMP: Authentication of Media via Provenance

VIEW 1 EXCERPT
CITES BACKGROUND

Deep HyperNetwork-Based MIMO Detection

VIEW 2 EXCERPTS
CITES BACKGROUND

Media Forensics and DeepFakes: an overview

VIEW 1 EXCERPT
CITES METHODS

A Surprising Density of Illusionable Natural Speech

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

VoxCeleb2: Deep Speaker Recognition

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

VoxCeleb: A Large-Scale Speaker Identification Dataset

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Image-to-Image Translation with Conditional Adversarial Networks

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Deep Face Recognition

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

VIEW 1 EXCERPT

Deep video portraits

VIEW 3 EXCERPTS