All's well that FID's well? Result quality and metric scores in GAN models for lip-sychronization tasks

Autor:	Geldhauser, Carina, Liljegren, Johan, Nordqvist, Pontus
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Statistics - Machine Learning 68T07
Druh dokumentu:	Working Paper
Popis:	We test the performance of GAN models for lip-synchronization. For this, we reimplement LipGAN in Pytorch, train it on the dataset GRID and compare it to our own variation, L1WGAN-GP, adapted to the LipGAN architecture and also trained on GRID.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.13810 Zobrazit plný text záznamu View this record from Arxiv