RETA3D: Real-Time Animatable 3D Gaussian Head Generation
Loading...
Date
2026
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
3D avatar GANs (generative adversarial networks) learn 3D priors from extensive collections of 2D portrait images. However, existing 3D avatar GANs either struggle with real-time performance or lack 3D consistency. To address these issues, we present RETA3D, a novel 3D GAN framework leveraging the efficiency of 3D Gaussian Splatting (3DGS). Our core contribution is a consecutive mesh-binding 3D Gaussian representation that tightly integrates 3D Gaussians with a FLAME mesh template via a novel local coordinate system defined by surface normals and head pose to ensure consistent animation. We also introduce a dynamic texture generation framework that separates static and dynamic texture components, significantly improving reenactment speed. This framework generates a static texture once and efficiently computes dynamic texture updates per-frame using a compact neural network conditioned on FLAME parameters.
Description
@inproceedings{10.2312:egs.20261025,
booktitle = {Eurographics 2026 - Short Papers},
editor = {},
title = {{RETA3D: Real-Time Animatable 3D Gaussian Head Generation}},
author = {Chen, Shu-Yu and Qiu, Chunshuo and Liu, Feng-Lin and Cao, Yanpei and Fu, Hongbo and Gao, Lin},
year = {2026},
publisher = {The Eurographics Association},
ISSN = {2309-5059},
ISBN = {978-3-03868-299-8},
DOI = {10.2312/egs.20261025}
}