Efficient 3D Gaussian Head Avatars for Edge Devices

arXiv:2610.09821 · cs.CV · Submitted 2026-10-07 · Read on arXiv

cs.CV

Submitted: 2026-10-07

Updated: 2026-10-07

License: http://creativecommons.org/licenses/by/4.0/

The gist: Generative 3D Gaussian head avatars provide high-quality, efficient rendering, but synthesising the Gaussian representation remains computationally expensive, limiting deployment on

Terminology

Abstract

Generative 3D Gaussian head avatars provide high-quality, efficient rendering, but synthesising the Gaussian representation remains computationally expensive, limiting deployment on resource-constrained and edge devices. We introduce an efficient generator architecture for unconditional 3D Gaussian head synthesis, based on a parameter-efficient synthesis block and depth-wise separable convolutions while retaining style-based conditioning. Our architecture reduces generator complexity without requiring model compression or quantisation. Compared with the baseline model, our approach reduces FLOPs by 94%, parameter count by 70%, and model size by 81%, while maintaining competitive generation quality. We further demonstrate practical CPU inference and browser-based execution on mobile devices using ONNX Runtime, enabling 3D Gaussian avatar synthesis without dedicated GPU hardware or application-specific software. In addition to conventional image-quality metrics, we evaluate multi-view consistency, training cost, and deployment performance. Code, trained models, and evaluation tools will be released publicly.

Sources

Related papers