cd /news/artificial-intelligence/cartoon-motion-model · home › topics › artificial-intelligence › article
[ARTICLE · art-170402] src=studios.disneyresearch.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Cartoon Motion Model

DisneyResearch|Studios researchers, with ETH Zurich, presented a framework at ACM SIGGRAPH Asia 2026 that generates and controls stylized 3D character motion by adapting a pre-trained human motion prior to hand-animated data. The framework uses robust data filtering for noisy production movements, an unconditional ControlNet trained for maximum alignment between motion capture and hand-animated domains, and a spectral inpainting scheme exposing parameters for exaggeration, source consistency and multi-character identities. The authors state the work bridges physical conformity and artistic stylization, enabling applications from retargeting human performances to character-to-character motion transfer.

by read1 min views1 publishedNov 16, 2026

In this work, we introduce a framework that enables generation and control of stylized 3D motion by leveraging a pre-trained human motion prior.

November 16, 2026

ACM SIGGRAPH Asia (2026)

Authors

Guilherme G. Haetinger (DisneyResearch|Studios/ETH Zurich)

Dhruv Agrawal (DisneyResearch|Studios/ETH Zurich)

Amit H. Bermano (DisneyResearch|Studios/ETH Zurich)

Robert W. Sumner (DisneyResearch|Studios/ETH Zurich)

Martin Guay (DisneyResearch|Studios)

Jakob Buhmann (DisneyResearch|Studios)

Cartoon Motion Model

Generative 3D motion has shown impressive capabilities for authoring movements, but the integration into animation production is currently hindered by the discrepancy between realistic human motion capture and the exaggerated, non-physical movements of stylized animated feature characters. Nonetheless, hand animated data is sparse, heterogeneous and incomplete, making it a challenging domain for data-hungry generative models. In this work, we introduce a framework that enables generation and control of stylized 3D motion by leveraging a pre-trained human motion prior. Our approach introduces robust data filtering techniques to handle inconsistent and noisy production movements. We train an unconditional ControlNet that eases adaptation by optimizing for maximum alignment between the motion capture and hand-animated domains. The generations of such model are also controllable through a spectral inpainting scheme that exposes parameters for exaggeration, source consistency and multi-character identities. We bridge the gap between physical conformity and artistic stylization and enable a diverse set of applications ranging from retargeting human performances to character-to-character motion transfer

── more in #artificial-intelligence 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/cartoon-motion-model] indexed:0 read:1min 2026-11-16 · —