SurFheadは、従来のガウシアンベースの手法では困難であった、頭部形状のストレッチやシアなどの複雑な変形を正確に捉え、高忠実度の頭部アバターを再構築する新しい手法である。
SurFhead is a novel method for reconstructing highly realistic and geometrically accurate dynamic head avatars from RGB videos, leveraging 2D Gaussian surfels, affine rig blending, and improved eyeball modeling for superior performance in challenging scenarios.
This paper introduces GAGAvatar, a novel framework that reconstructs a highly detailed and animatable 3D head avatar from a single image, achieving real-time expression control and rendering using 3D Gaussian Splatting and a novel dual-lifting method.