zhanglonghao1992 / One-Shot_Free-View_Neural_Talking_Head_Synthesis Public

Notifications You must be signed in to change notification settings
Fork 144
Star 807

Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"

807 stars 144 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 28 Commits
config		config
modules		modules
sync_batchnorm		sync_batchnorm
README.md		README.md
animate.py		animate.py
augmentation.py		augmentation.py
crop-video.py		crop-video.py
demo.py		demo.py
frames_dataset.py		frames_dataset.py
logger.py		logger.py
run.py		run.py
train.py		train.py

Repository files navigation

One-Shot Free-View Neural Talking Head Synthesis

Unofficial pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"

Driving | FOMM | Ours:

Free-View:

Train:

python run.py --config config/vox-256.yaml --device_ids 0,1,2,3,4,5,6,7

Demo:

python demo.py --config config/vox-256.yaml --checkpoint path/to/checkpoint --source_image path/to/source --driving_video path/to/driving --relative --adapt_scale --find_best_frame

free-view (e.g. yaw=20, pitch=roll=0):

python demo.py --config config/vox-256.yaml --checkpoint path/to/checkpoint --source_image path/to/source --driving_video path/to/driving --relative --adapt_scale --find_best_frame --free_view --yaw 20 --pitch 0 --row 0

Note: run crop-video.py --inp driving_video.mp4 to get crop suggestions and crop the driving video as prompted.