Head Avatar
Head avatar research focuses on creating realistic, animatable 3D models of human heads for applications in virtual and augmented reality, gaming, and film. Current efforts concentrate on developing efficient and high-fidelity models using various architectures, including neural radiance fields (NeRFs), 3D Gaussian splatting, and parametric models like 3D Morphable Models (3DMMs), often incorporating techniques like diffusion models and GANs for enhanced realism and control. These advancements are significant because they enable more immersive and interactive experiences in various digital environments, pushing the boundaries of realistic human representation in computer graphics.
Papers
GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image
Chong Bao, Yinda Zhang, Yuan Li, Xiyu Zhang, Bangbang Yang, Hujun Bao, Marc Pollefeys, Guofeng Zhang, Zhaopeng Cui
Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes
Ziqian Bai, Feitong Tan, Sean Fanello, Rohit Pandey, Mingsong Dou, Shichen Liu, Ping Tan, Yinda Zhang