cd /news/computer-vision/designing-animatable-stylized-charac… · home › topics › computer-vision › article
[ARTICLE · art-170403] src=studios.disneyresearch.com ↗ pub= topic=computer-vision verified=true sentiment=↑ positive

Designing Animatable Stylized Characters with Multi-Layer 3D Gaussians

DisneyResearch|Studios researchers Wenqing Wang, Clara Fernandez, Yang Zhang and Abdelaziz Djelouah presented a framework at ACM SIGGRAPH Asia 2026 that produces fully rigged, animatable stylized characters from a single image, with optional additional references. The system couples a deformable mesh with a multi-layer Gaussian field to enable layered rendering, stable articulation and view-dependent appearance, and accelerates fitting with generative priors in 3D and image space. The authors report results that match or exceed prior approaches while better meeting goals of alignment and controllability for stylized 4D character synthesis, and the framework supports an artist-in-the-loop workflow for assembling or extending a character sheet through iterative image edits.

by read1 min views1 publishedNov 16, 2026

In this work, we introduce a unified framework that produces fully rigged, animatable characters from a single image, while supporting additional references when available.

November 16, 2026

ACM SIGGRAPH Asia (2026)

Authors

Wenqing Wang (DisneyResearch|Studios/ETH Zurich)

Clara Fernandez (DisneyResearch|Studios)

Yang Zhang (DisneyResearch|Studios) Abdelaziz Djelouah (DisneyResearch|Studios)

Designing Animatable Stylized Characters with Multi-Layer 3D Gaussians

Animatable stylized characters are central to animation pipelines, yet transforming a few hand-drawn references into a rigged, editable, and renderable asset remains labor-intensive. Existing generative methods tend to deviate from the original artist-provided designs, while single image based methods offer unclear paths for integration into artist workflows. We introduce a unified framework that produces fully rigged, animatable characters from a single image, while supporting additional references when available. The core representation couples a deformable mesh with a multi-layer Gaussian field, enabling layered rendering, stable articulation, and rich view-dependent appearance. Fitting is accelerated by generative priors in 3D and image space. Beyond single-image animation, the system supports an artist-in the-loop workflow for assembling or extending a character sheet through iterative image edits that are straightforward to model and control in a Gaussian formulation. Our design allows for decoupled modules that learn complex appearance phenomena, such as line work and lighting. We report results that match or exceed prior approaches while better matching goals of alignment and controllability, for stylized 4D character synthesis.

── more in #computer-vision 4 stories · sorted by recency
── more on @disneyresearch|studios 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/designing-animatable…] indexed:0 read:1min 2026-11-16 · —