AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars

TL;DR

AGORA is a novel framework that generates high-fidelity, animatable 3D head avatars using a GAN-based approach, enabling real-time rendering and on-device animation with state-of-the-art quality.

Contribution

It extends 3D Gaussian Splatting with adversarial training to produce controllable, realistic, and animatable 3D head avatars suitable for real-time applications.

Findings

Achieves 560 FPS rendering on GPU and 60 FPS on mobile.

Outperforms existing methods in avatar realism and controllability.

Provides a simple inference-time approach for on-device animation.

Abstract

The generation of high-fidelity, animatable 3D human avatars remains a core challenge in computer graphics and vision, with applications in VR, telepresence, and entertainment. Existing approaches based on implicit representations like NeRFs suffer from slow rendering and dynamic inconsistencies, while 3D Gaussian Splatting (3DGS) methods are typically limited to static head generation, lacking dynamic control. We bridge this gap by introducing AGORA, a novel framework that extends 3DGS within a generative adversarial network to produce animatable avatars. Our formulation combines spatial shape conditioning with a dual-discriminator training strategy that supervises both rendered appearance and synthetic geometry cues, improving expression fidelity and controllability. To enable practical deployment, we further introduce a simple inference-time approach that extracts Gaussian blendshapes and reuses them for animation on-device. AGORA generates avatars that are visually realistic, precisely controllable, and achieves state-of-the-art performance among animatable generative head-avatar methods. Quantitatively, we render at 560 FPS on a single GPU and 60 FPS on mobile phones, marking a significant step toward practical, high-performance digital humans. Project website: https://ramazan793.github.io/AGORA/