audio2face_mm2023

audio2face_mm2023 copied to clipboard

文章里写的推理时间0.007s是指HuBERT 和 ResNet1D总的时间吗？

1

文中：Our backbone is built on a pretrained HuBERT model and a ResNet1D network, which preserves high-frequency details of facial movements. During implementation, our backbone synthesizes one second of facial animations...

zgyh001

"mesh sequence" when performing inference

2

Hi, thanks for your great work. I would like to know how to prepare the "mesh sequence" input data when performing inference with unseen audio data？

Zrduan724

Hi! Thanks for sharing the code, data and models. I would like to try running your code and look at the results. I am not in China and I am...

cravisjan97

您好，非常感谢您的工作！ 在Dataset preparation这一栏中，我发现您对vocaset这一数据集进行了处理，请问您是以何种方式进行处理的？

ylark1203