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
1.5k Dec 30, 2022
4.7k Dec 31, 2022
771 Dec 15, 2022
252 Sep 16, 2022
8 Aug 28, 2022
110 Dec 23, 2022
13 Sep 15, 2022
17 Jan 03, 2023
3.5k Jan 03, 2023
69 Dec 20, 2022
0 Dec 23, 2021
41 Nov 30, 2022
35 Jul 29, 2022
99 Dec 11, 2022
115 Jan 02, 2023
77 Dec 27, 2022
48 Dec 20, 2022
1 Jan 20, 2022
6 Nov 10, 2022
7 Aug 07, 2022