Hierarchical cross-modal talking face generationwith dynamic pixel-wise loss
We devise a cascade GAN approach to generate talking face video, which is robust to
different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead …
different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead …
[PDF][PDF] Hierarchical Cross-Modal Talking Face Generation with Dynamic Pixel-Wise Loss
LCRKM Zhiyao, DC Xu - researchgate.net
We devise a cascade GAN approach to generate talking face video, which is robust to
different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead …
different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead …
Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss
L Chen, RK Maddox, Z Duan, C Xu - arXiv e-prints, 2019 - ui.adsabs.harvard.edu
We devise a cascade GAN approach to generate talking face video, which is robust to
different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead …
different face shapes, view angles, facial characteristics, and noisy audio conditions. Instead …