Generating Editable Head Avatars with 3D Gaussian GANs

TL;DR

This paper introduces a novel method for generating editable and animatable 3D head avatars by combining 3D Gaussian Splatting with a 3D Morphable Model, improving control and realism over previous implicit field-based methods.

Contribution

The paper proposes the Editable Gaussian Head (EG-Head) model that integrates 3DMM and texture maps with 3D Gaussian Splatting for enhanced editability and animation control of 3D head avatars.

Findings

Achieves high-quality 3D-aware synthesis with improved controllability.

Enables precise expression and texture editing while maintaining identity.

Demonstrates superior flexibility in deformation and animation control.

Abstract

Generating animatable and editable 3D head avatars is essential for various applications in computer vision and graphics. Traditional 3D-aware generative adversarial networks (GANs), often using implicit fields like Neural Radiance Fields (NeRF), achieve photorealistic and view-consistent 3D head synthesis. However, these methods face limitations in deformation flexibility and editability, hindering the creation of lifelike and easily modifiable 3D heads. We propose a novel approach that enhances the editability and animation control of 3D head avatars by incorporating 3D Gaussian Splatting (3DGS) as an explicit 3D representation. This method enables easier illumination control and improved editability. Central to our approach is the Editable Gaussian Head (EG-Head) model, which combines a 3D Morphable Model (3DMM) with texture maps, allowing precise expression control and flexible texture editing for accurate animation while preserving identity. To capture complex non-facial geometries like hair, we use an auxiliary set of 3DGS and tri-plane features. Extensive experiments demonstrate that our approach delivers high-quality 3D-aware synthesis with state-of-the-art controllability. Our code and models are available at https://github.com/liguohao96/EGG3D.