Hangz-nju-cuhk / Talking-Face-Generation-DAVS

Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)
MIT License
816 stars 173 forks source link

Run testing script result not as good as demo #45

Open zhhezhhe opened 4 years ago

zhhezhhe commented 4 years ago

Thank you for the great work! I run python test_all.py --test_root ./0572_0019_0003/video --test_type video --test_audio_video_length 99

but my results are not the same as the demo video and jitter a lot. Do you know what the problem is?

Hangz-nju-cuhk commented 4 years ago

@zhhezhhe Hi, it should jitter a bit because I used stabilization for post-processing.

zhhezhhe commented 4 years ago

@zhhezhhe Hi, it should jitter a bit because I used stabilization for post-processing.

Thank you for the quick reply! I checked the readme and found about Postprocessing Details. You mentioned that you used Subspace Video Stabilization, could you kindly point me to the code?