Reduces high-quality 3D head avatar creation time from over 24 hours to 0.5 seconds per frame.
March 18, 2026
Original Paper
Feed-forward Gaussian Registration for Head Avatar Creation and Editing
arXiv · 2603.15811
The Takeaway
By using registration-guided attention and feed-forward Gaussian splat texture prediction, it removes the need for expensive per-subject optimization. This enables real-time personalized avatar creation and semantic editing from calibrated multi-view video.
From the abstract
We present MATCH (Multi-view Avatars from Topologically Corresponding Heads), a multi-view Gaussian registration method for high-quality head avatar creation and editing. State-of-the-art multi-view head avatar methods require time-consuming head tracking followed by expensive avatar optimization, often resulting in a total creation time of more than one day. MATCH, in contrast, directly predicts Gaussian splat textures in correspondence from calibrated multi-view images in just 0.5 seconds per