FAGhead: Fully Animate Gaussian Head from Monocular Videos.
Yixin XuanXinyang LiGongxin YaoShiwei ZhouDonghui SunXiaoxin ChenYu PanPublished in: CoRR (2024)
Keyphrases
- image sequences
- motion capture data
- video frames
- video sequences
- view invariant
- facial animation
- video analysis
- maximum likelihood
- human activities
- calibrated cameras
- real time
- video data
- video content
- model based tracking
- motion capture
- video database
- gaussian distribution
- human motion
- gaussian mixture model
- optical flow
- dynamic scenes
- video clips
- key frames
- video streams
- independently moving objects
- pose estimation