search

Hangz-nju-cuhk / Talking-Face_PC-AVS

Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)
Creative Commons Attribution 4.0 International
916 stars 169 forks source link

can you share the details of the augmentation generating non-id space #38

Closed makpia closed 2 years ago

makpia commented 3 years ago

i notice that you mentioned the paper "Neural Head Reenactment with Latent Pose Descriptors" in an issue about non-id space. i tried the augmentation used in their code, but it seems different from yours, with fewer changes. this part seems vital considering the non-id space is vital, promising the model to distangle the id feature and pose feature. so i would like to know the augmentation details in your paper. can you share it to us?

Hangz-nju-cuhk commented 3 years ago

Hi, the code for our augmentation is already in data/base_dataset.py. I think it can also work if you use their augmentation. The reason that the augmentations are different is that their code was not publically available when I was working on this one.

makpia commented 3 years ago

Hi, the code for our augmentation is already in data/base_dataset.py. I think it can also work if you use their augmentation. The reason that the augmentations are different is that their code was not publically available when I was working on this one.

thanks for the reply! i missed the part in this file. i will try it later. thank you!