search

harlanhong / CVPR2022-DaGAN

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
https://harlanhong.github.io/publications/dagan.html
Other
957 stars 125 forks source link

real-time property of FDN #55

Closed Bruce-yu199 closed 1 year ago

Bruce-yu199 commented 1 year ago

hi, DaGAN is fantastic! i'm interested in the face depth network, and i want to know the real-time of FDN, or in other word, how much time it takes to infer a depth map of an input picture? because i want to know if it is suitable for mobile platform.

harlanhong commented 1 year ago

It can perform in real-time, at about 30 fps.

Bruce-yu199 commented 1 year ago

It can perform in real-time, at about 30 fps.

Thanks!