Relightable Full-Body Gaussian Codec Avatars

Shaofei Wang; Tomas Simon; Igor Santesteban; Timur M. Bagautdinov; Junxuan Li; Vasu Agrawal; Fabian Prada; Shoou-I Yu; Pace Nalbone; Matt Gramlich; Roman Lubachersky; Chenglei Wu; Javier Romero; Jason M. Saragih; Michael Zollhöfer; Andreas Geiger; Siyu Tang; Shunsuke Saito

doi:10.1145/3721238.3730739

SIGGRAPH2025顶会

Relightable Full-Body Gaussian Codec Avatars

Shaofei Wang, Tomas Simon, Igor Santesteban, Timur M. Bagautdinov, Junxuan Li, Vasu Agrawal, Fabian Prada, Shoou-I Yu, Pace Nalbone, Matt Gramlich, Roman Lubachersky, Chenglei Wu

arXiv DOI 出版方

2025年份

6被引次数

11顶会引用

摘要

We propose Relightable Full-Body Gaussian Codec Avatars, a new approach for modeling relightable full-body avatars with fine-grained details including face and hands.The unique challenge for relighting full-body avatars lies in the large deformations caused by body articulation and the resulting impact on appearance caused by light transport.Changes in body pose can dramatically change the orientation of body surfaces with respect to USA,