CGRG Logo
<- Back To Publications
Latent Space Skinning: Learning Compact Representations for Mesh Animations

Latent Space Skinning: Learning Compact Representations for Mesh Animations

G. Drongoulas, G. Tsopouridis, A. Aristidou, and I. Fudos

The 25th ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA) posters, 2026

Latent-Space Skinning (LSS) is a neural character animation framework that replaces explicit skinning weights with a shared latent representation of skeletal motion and rest-pose geometry, which is decoded into per-vertex mesh deformations over time. This compact and expressive latent space enables high compression ratios, accurate reconstruction, and intuitive motion manipulation operations such as blending and cross-character transfer.

Download PDFPresentationVideoView Code

Abstract

Latent-Space Skinning (LSS) is a neural character animation framework that replaces explicit skinning weights with a shared latent representation of skeletal motion and rest-pose geometry, which is decoded into per-vertex mesh deformations over time. This compact and expressive latent space enables high compression ratios, accurate reconstruction, and intuitive motion manipulation operations such as blending and cross-character transfer. The fast forward video of the conference is available here: link.

BibTeX Citation

@inproceedings{drongoulas2026,
author = "G. Drongoulas, G. Tsopouridis, A. Aristidou, and I. Fudos",
title = "Latent Space Skinning: Learning Compact Representations for Mesh Animations",
booktitle = "ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA) posters",
 year = {2026},
 location = {Barcelona},
 publisher = {Eurographics}
}