Ruizhi Cheng

Thank you for your awesome work! I would like to ask can I use this framework to generate/predict the new audio frame based on the previous audio information and visual...

Incorporate FAST-Snarf into X-Avatar

1

Thanks for the great work! Hello, in your supplementary material, you mentioned in order to improve rendering speed, a potential solution is to use [FAST-Snarf](https://github.com/xuchen-ethz/fast-snarf) in X-Avatar. I would like...

How to fine-tune the pre-trained model on my dataset?

9

Hello, I would like to ask how can I load the pre-trained model and fine-tune it on my self-collected dataset?

Thank you for your outstanding work! I understand that the current solution operates on a single-frame basis with 2D input, similar to GeneFace++. While we have a video-driven solution, it...