# Hybrid Explicit Representation for Ultra-Realistic Head Avatars

arXiv: https://arxiv.org/abs/2403.11453 · HTML: https://mlsanity.com/paper/2403.11453/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2024.

## Built on by (most cited first, 6 of 6)

- [EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding](https://mlsanity.com/paper/2412.04380/) (2024)
- [CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians](https://mlsanity.com/paper/2505.21041/) (2025)
- [AI-Driven Innovations in Volumetric Video Streaming: A Review](https://mlsanity.com/paper/2412.12208/) (2024)
- [SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction](https://mlsanity.com/paper/2606.15659/) (2026)
- [MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling](https://mlsanity.com/paper/2609.12850/) (2026)
- [Fresco++: Frequency-Guided and Canonical-Consistent Optimization for Fine-Grained Head Avatar Modeling](https://mlsanity.com/paper/2610.11412/) (2026)

## Abstract (arXiv)

We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time (>30fps at 2048 × 1334 resolution). First, we propose a hybrid explicit representation that combines the advantages of two primitive-based efficient rendering techniques. UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures. In the pipeline of modeling an avatar, after tracking parametric models based on captured multi-view RGB videos, our goal is to simultaneously optimize the texture and opacity map of mesh, as well as a set of 3D Gaussian splats localized and rigged onto the mesh facets. Specifically, we perform α-blending on the color and opacity values based on the merged and re-ordered z-buffer from the rasterization results of mesh and 3DGS. This process involves the mesh and 3DGS adaptively fitting the captured visual information to outline a high-fidelity digital avatar. To avoid artifacts caused by Gaussian splats crossing the mesh facets, we design a stable hybrid depth sorting strategy. Experiments illustrate that our modeled results exceed those of state-of-the-art approaches.