Jin Liu

Hi， thanks for the great work! In paper Section 3.2, you mention that **"We generate intermediate 2D landmark positions ``p_j`` by interpolating between ``e_s`` and ``e_t``."** I want to know...

Thank you for the great work. Is there any plan for the code release of Audio-Driven Facial Reenactment? The result is really impressive~ Best wishes.

Thank you for the great work! I follow the instruction mentioned in [First-Order](https://github.com/AliaksandrSiarohin/video-preprocessing) to download the videos and crop them for train and test. However, in audio driven generation, the...

About Dynamic Timing Warping preprocess mfcc features

3

Given two audio features of shape [N1, 28, 12] and [N2, 28, 12], could you please show me the demo code of align them using DTW methods? When training the...

About the DECODER used in the Cross-reconstruction Emotion Disentanglement Module

1

Thank you for the great work and the disentanglement of content and emotion features are really novel. When I re-product this module, I get frustrated about the decoder structure. Could...

Questions about part of the network input ΔF_s

1

Thank you for your great work! But I am confused about the input ΔF_s. In the paper, each f_i(W*H*2) in ΔF_s is a spatial field map indicating the landmark difference....