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

Is the audio supported in the generated video? #39

Closed tikitong closed 1 year ago

tikitong commented 1 year ago

Is there a way to keep the audio in the generated video? Many thanks.

harlanhong commented 1 year ago

will go back to you after 8pm, you know, ICLR :)

harlanhong commented 1 year ago

Sure, you can use a tool to divide a diving video into audio and video frames, then merge the audio and generated video frames. I think there are many tools can achieve this goal.

tikitong commented 1 year ago

Yes, thank you for taking the time to reply. I used ffmpeg:

#extract the audio
ffmpeg -i driving_video.mp4 audio.wav

#paste on demo.mp4 generated
ffmpeg -i demo.mp4 -i audio.wav -map 0:v -map 1:a -c:v copy -shortest output.mp4