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.
Acknowlegement:
Thanks to NV, AliaksandrSiarohin and DeepHeadPose
48 Nov 09, 2022
290 Jan 09, 2023
6 May 25, 2022
42 Dec 09, 2022
18 Dec 19, 2022
38 Dec 12, 2022
3 Apr 27, 2022
78 Dec 07, 2022
78 Dec 02, 2022
10 Jul 27, 2021
0 Jan 11, 2022
27 Dec 22, 2022
15 Dec 30, 2021
2 Oct 10, 2022
5 Nov 24, 2021
125 Dec 06, 2022
17 Dec 08, 2022
13 Oct 27, 2022
311 Jan 06, 2023
[email protected]">
11 Dec 03, 2022