RETA3D: Real-Time Animatable 3D Gaussian Head Generation

Simple item page
dc.contributor.authorChen, Shu-Yu
dc.contributor.authorQiu, Chunshuo
dc.contributor.authorLiu, Feng-Lin
dc.contributor.authorCao, Yanpei
dc.contributor.authorFu, Hongbo
dc.contributor.authorGao, Lin
dc.date.accessioned2026-04-20T08:42:04Z
dc.date.available2026-04-20T08:42:04Z
dc.date.issued2026
dc.description.abstract3D 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.
dc.description.sectionheadersRendering Representations & GPU Pipelines
dc.description.seriesinformationEurographics 2026 - Short Papers
dc.identifier.doi10.2312/egs.20261025
dc.identifier.isbn978-3-03868-299-8
dc.identifier.issn2309-5059
dc.identifier.pages4 pages
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20261025
dc.identifier.urihttps://doi.org/10.2312/egs.20261025
dc.publisherThe Eurographics Association
dc.rightsCC-BY-4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectAnimation
dc.subject3D imaging
dc.subjectAdversarial learning
dc.titleRETA3D: Real-Time Animatable 3D Gaussian Head Generation
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
egs20261025.pdf
Size:
12.26 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
short1028_mm.pdf
Size:
3.58 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
short1028_mm_crc1.mp4
Size:
175.4 MB
Format:
Video MP4
Download
Collections
EG 2026 - Short Papers