Facke: a Survey on Generative Models for Face Swapping

06/22/2022
by   Wei Jiang, et al.
0

In this work, we investigate into the performance of mainstream neural generative models on the very task of swapping faces. We have experimented on CVAE, CGAN, CVAE-GAN, and conditioned diffusion models. Existing finely trained models have already managed to produce fake faces (Facke) indistinguishable to the naked eye as well as achieve high objective metrics. We perform a comparison among them and analyze their pros and cons. Furthermore, we proposed some promising tricks though they do not apply to this task.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 11

research
09/13/2023

Unbiased Face Synthesis With Diffusion Models: Are We There Yet?

Text-to-image diffusion models have achieved widespread popularity due t...
research
03/27/2020

One-Shot GAN Generated Fake Face Detection

Fake face detection is a significant challenge for intelligent systems a...
research
12/20/2013

Learning Generative Models with Visual Attention

Attention has long been proposed by psychologists as important for effec...
research
10/02/2022

Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2

The field of image synthesis has made great strides in the last couple o...
research
02/20/2023

Towards Universal Fake Image Detectors that Generalize Across Generative Models

With generative models proliferating at a rapid rate, there is a growing...
research
09/16/2022

Can There be Art Without an Artist?

Generative Adversarial Network (GAN) based art has proliferated in the p...
research
12/28/2022

How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection

With the proliferation of deep generative models, deepfakes are improvin...

Please sign up or login with your details

Forgot password? Click here to reset