search

gafniguy / 4D-Facial-Avatars

Dynamic Neural Radiance Fields for Monocular 4D Facial Avater Reconstruction
679 stars 67 forks source link

How to get continuous video, not individual rendered images? #31

Closed soom1017 closed 2 years ago

soom1017 commented 2 years ago

Thanks for great contribution!! However, I'm getting problem with the same issue https://github.com/gafniguy/4D-Facial-Avatars/issues/29 . How can I get different pose & expression frame images, and final video just as in the sample? Set line 420 to None, but too many errors... Can I get codes to synthesize a video?

gafniguy commented 2 years ago

Once you have a folder with individual frames, you can write out a video drom it: if you don't have ffmpeg, install it: sudo apt update sudo apt install ffmpeg Run ffmpeg command to write out the video:

ffmpeg -i path_to_rendered_images/%04d.png -pix_fmt yuv420p -crf 19 ./out.mp4

soom1017 commented 2 years ago

Solved. Thank you!!