mlsanityData to 7 Oct 2026

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

arXiv 2212.13810 ↗First posted 28 Dec 2022cs.CV stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 28 Dec 2022.

Builds on

13 of 23 references.

References · 13

  1. 2017Improved Training of Wasserstein GANscited by 2,223
  2. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  3. 2018Deep Audio-Visual Speech Recognitioncited by 318
  4. 2018Talking Face Generation by Adversarially Disentangled Audio-Visual Representationcited by 212
  5. 2017Video Frame Synthesis using Deep Voxel Flowcited by 209
  6. 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
  7. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 161
  8. 2018Lip Movements Generation at a Glancecited by 154
  9. 2019Realistic Speech-Driven Facial Animation with GANscited by 142
  10. 2020Towards Automatic Face-to-Face Translationcited by 95
  11. 2018An empirical study on evaluation metrics of generative adversarial networkscited by 81
  12. 2017ObamaNet: Photo-realistic lip-sync from textcited by 42
1 more
  1. 2020Iterative Text-based Editing of Talking-heads Using Neural Retargetingcited by 21

Built on by

Not cited yet.