search

YuanxunLu / LiveSpeechPortraits

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)
MIT License
1.16k stars 200 forks source link

Generate live speech for person arbitrary!! #31

Closed pegahs1993 closed 2 years ago

pegahs1993 commented 2 years ago

Thanks for sharing such nice work Can I run this code for person arbitrary? How the information in the folder is obtained for each person?

Thank you for your help!

TimmmYang commented 2 years ago

You can check this paper in Section 4. about implementation details.

pegahs1993 commented 2 years ago

You can check this paper in Section 4. about implementation details.

I read section 4, but I do not know where to start?! What code should I use to make facial landmarks? How to generate npz and npy files? Where can I read cropped video as input?

Thank you in advance

YuanxunLu commented 2 years ago

The proposed method is person-specific, you need to train new models for different people. You can check issue #19 for more details.