Abstract: With the fast-evolving field of education, there is an increase in the demand for intelligent tutorial systems that can adapt to the diverse learning needs of individual students. This ...

PantoMatrix is an Open-Source and research project to generate 3D body and face animation from speech. It works as an API inputs speech audio and outputs body and face motion parameters. You may ...

We propose InfiniteTalk , a novel sparse-frame video dubbing framework. Given an input video and audio track, InfiniteTalk synthesizes a new video with accurate lip synchronization while ...