[NeurIPS '24] Generalizable and Animatable Gaussian Head Avatar
Remark: Runs at 67 fps as reported and comes with code🤯
Contributions:
• We propose GAGAvatar, which to our knowledge is the first generalizable 3D Gaussian head avatar framework that achieves single forward reconstruction and real-time reenactment.
• To achieve this, we propose a dual-lifting method to lift Gaussians from a single image and introduce a method that uses 3DMM priors to constrain the lifting process.
• We combine 3DMM priors and 3D Gaussians to accurately transfer expression information while avoiding redundant computations.
[NeurIPS '24] Generalizable and Animatable Gaussian Head Avatar
Remark: Runs at 67 fps as reported and comes with code🤯
Contributions:
• We propose GAGAvatar, which to our knowledge is the first generalizable 3D Gaussian head avatar framework that achieves single forward reconstruction and real-time reenactment.
• To achieve this, we propose a dual-lifting method to lift Gaussians from a single image and introduce a method that uses 3DMM priors to constrain the lifting process.
• We combine 3DMM priors and 3D Gaussians to accurately transfer expression information while avoiding redundant computations.
#ICLR2024#AIGC#3D Are you interested at building 3D human avatars? Are you troubled by the unclear details and inaccurate expression of avatars?
If yes, please check our GPAvatar, code&model are released!
https://t.co/qVREakH88T
https://t.co/R4ORQMXrXi
https://t.co/df9Pr3AyVV