Year: 2022
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Jiang, Wei, Dong, Wentao
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4320166213