Human Avatar
Human avatar research aims to create realistic and controllable 3D digital representations of humans, focusing on accurate geometry, appearance, and dynamic animation. Current efforts heavily utilize neural networks, particularly those based on Gaussian splatting and neural radiance fields, along with diffusion models for texture and style control, often incorporating physics-based simulations for realistic clothing and movement. This field is significant for its applications in entertainment, virtual and augmented reality, and human-computer interaction, offering advancements in realistic character animation, personalized virtual experiences, and improved training simulations.
Papers
Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion
Zeyu Zhang, Yiran Wang, Biao Wu, Shuo Chen, Zhiyuan Zhang, Shiya Huang, Wenbo Zhang, Meng Fang, Ling Chen, Yang Zhao
HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos
Qifeng Chen, Rengan Xie, Kai Huang, Qi Wang, Wenting Zheng, Rong Li, Yuchi Huo