search

microsoft / NUWA

A unified 3D Transformer Pipeline for visual synthesis
2.81k stars 163 forks source link

Paper - Possible (minor) error #3

Closed afiaka87 closed 2 years ago

afiaka87 commented 2 years ago

In this paper, we show that simply using 2D VQ-GAN to encode each frame of a video can also generate temporal consistency videos and at the same time benefit from both image and video data.

In the paper, I believe you mean "temporally consistent" here. Subtle change in wording.

chenfei-wu commented 2 years ago

Thank you for your suggestion!

afiaka87 commented 2 years ago

No problem - excited to see the results!