Unofficial pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"
Driving | FOMM | Ours:
Free-View:
python run.py --config config/vox-256.yaml --device_ids 0,1,2,3,4,5,6,7
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.
| ------- | Train Set | Baidu Netdisk | Google Drive |
|---|---|---|---|
| Vox-256 | VoxCeleb-v1 | Baidu (PW: c0tc) | soon |
| Vox-256 | VoxCeleb-v2 | soon | soon |
| Vox-512 | VoxCeleb-v2 | soon | soon |
Note: It is recommended that Yaw, Pitch and Roll are within ±45°, ±20° and ±20° respectively for free-view synthesis.
Thanks to NV, AliaksandrSiarohin and DeepHeadPose