GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
This work addresses the challenge of creating realistic and animatable 3D head avatars for applications in virtual reality, gaming, and digital humans, representing a domain-specific advancement.
The paper tackles the problem of constructing vivid 3D head avatars for animation by introducing GaussianHead, which uses anisotropic 3D Gaussians with a learnable derivation scheme, resulting in high-fidelity renderings that outperform state-of-the-art methods in reconstruction, cross-identity reenactment, and novel view synthesis.
Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging. This paper presents GaussianHead, which models the actional human head with anisotropic 3D Gaussians. In our framework, a motion deformation field and multi-resolution tri-plane are constructed respectively to deal with the head's dynamic geometry and complex texture. Notably, we impose an exclusive derivation scheme on each Gaussian, which generates its multiple doppelgangers through a set of learnable parameters for position transformation. With this design, we can compactly and accurately encode the appearance information of Gaussians, even those fitting the head's particular components with sophisticated structures. In addition, an inherited derivation strategy for newly added Gaussians is adopted to facilitate training acceleration. Extensive experiments show that our method can produce high-fidelity renderings, outperforming state-of-the-art approaches in reconstruction, cross-identity reenactment, and novel view synthesis tasks. Our code is available at: https://github.com/chiehwangs/gaussian-head.