Yango

Hi, is there any method to convert trainingset, the 4D pairs, to audio-blendshape format? maybe some situations don't need so accurate information, such as generate animoji and other avatar persons....

"we attach a video with high-resolution rotating rendered mesh results, which showcases the quality and accuracy of the texture completion and geometric details acquisitio" thanks for your wonderful work! BTW.,...

some problems about training.

1

I wonder how many epochs should be set to train the model, and should the learning rate be updated during training?

some issues about data set

50

In TrainingSetPreparation.py,  I wonder whats the format of LFPW or HELEN and how to ensure that images corresponding to data?

不知道可以不可以用resnet换掉第一层的vgg16

how to make inference on ted dataset

3

hello， thanks for excellent work! I wander how to make inference on Ted dataset, when I try default setting like Vox using Ted pretrained model, the generated video is terrible,...