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

12/28/2022

∙

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.

READ FULL TEXT

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

Tabular GANs for uneven distribution

Application of WGAN-GP in recommendation and Questioning the relevance of GAN-based approaches

Synthesizing Property Casualty Ratemaking Datasets using Generative Adversarial Networks

Utilizing synchronization to partition power networks into microgrids

Image Augmentation for Satellite Images

AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework

Poly-GAN: Multi-Conditioned GAN for Fashion Synthesis

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

Related Research

Tabular GANs for uneven distribution

Application of WGAN-GP in recommendation and Questioning the relevance of GAN-based approaches

Synthesizing Property Casualty Ratemaking Datasets using Generative Adversarial Networks

Utilizing synchronization to partition power networks into microgrids

Image Augmentation for Satellite Images

AuthorGAN: Improving GAN Reproducibility using a Modular GAN Framework

Poly-GAN: Multi-Conditioned GAN for Fashion Synthesis