works on
3d gaussian representation 1facial motion refinement 1head avatar reconstruction 1incremental reconstruction 1sparse-to-dense learning 1transformer architecture 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

Jianjiang Yao, Ke Xian, Renxiang Dai +1

The paper introduces FFAvatar, a transformer-based 3D Gaussian framework that can quickly build high‑quality, animatable 4D head avatars from one or more portrait images, supportin…