Gaussian Pixel Codec Avatars: A Hybrid Representation for Efficient Rendering Abstract (excerpt): GPiCA utilizes a unique hybrid representation combining a triangle mesh and anisotropic 3D Gaussians. This combination maximizes memory and rendering efficiency while maintaining a photorealistic appearance. - The triangle mesh is highly efficient in representing surface areas like facial skin. - The 3D Gaussians effectively handle non-surface areas such as hair and beard. To this end, we develop a unified differentiable rendering pipeline that treats the mesh as a semi-transparent layer within the volumetric rendering paradigm of 3D Gaussian Splatting. We train neural networks to decode a facial expression code into three components: 1. A 3D face mesh, 2. An RGBA texture, 3. A set of 3D Gaussians. These components are rendered simultaneously in a unified rendering engine. The networks are trained using multi-view image supervision. Our results demonstrate that GPiCA achieves the realism of purely Gaussian-based avatars while matching the rendering performance of mesh-based avatars.