One-Shot_Free-View_Neural_Talking_Head_Synthesis
One-Shot_Free-View_Neural_Talking_Head_Synthesis copied to clipboard
Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"
Thank you for your great work! During my training, I found that the voxceleb dataset contains millions of pieces of data, and num_repeat=75, which causes that an epoch is 8...
Hi, Thank you for your implementation!. I am using your code to training on V100. I used - spade-based generator - estimate_jacobian=False - I change `num_repeats` to 1 instead of...
Hi ! Did anyone manage to obtain the 512 model and would accept to share it ? I'm sure it could please a lot of people ! Thanks in advance
大佬您好,请问检测到的关键点怎么单独保存呀,关键点只出现在keypoint_detecotr.py中吗,我想计算一下压缩率嘞
The official website removed the dataset link could you provide the vox dataset?
Vox-512
Hello, the published model test results are very good, can the author share the 512 model as soon as possible, thank you very much!
Hi @zhanglonghao1992 , Thanks for sharing your implementation of the paper! As I understand there is difference from the first to the last version of the paper regarding the using...
``` onur@onur-XPS-15-7590:~/git-repos/One-Shot_Free-View_Neural_Talking_Head_Synthesis$ python3 demo.py --config config/vox-256-spade.yaml --checkpoint 00000189-checkpoint.pth.tar --source_image example-images/me.jpg --driving_video crop.mp4 --relative --adapt_scale --find_best_frame --free_view --yaw 20 --pitch 0 --roll 0 /home/onur/git-repos/One-Shot_Free-View_Neural_Talking_Head_Synthesis/demo.py:24: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated,...
``` from skimage.draw import circle ImportError: cannot import name 'circle' from 'skimage.draw' (/home/onur/.local/lib/python3.9/site-packages/skimage/draw/__init__.py) ``` I've changed the function to `skimage.draw.disk()` and now I am getting this error. `skimage.draw.ellipse()` returns the...
Thank you so much for publishing this great implementation! I'd like to use the pre-trained model in order to drive a specific face to talk, by another driving person's talking...