About this paper
DyCraft improves long-horizon 3D animation by decomposing it into planned static scenes, keyframe storyboards, and local motion authoring to reduce physical errors.
While frontier coding agents can generate high-quality 3D scenes and articulated assets, they struggle to create coherent long-horizon animations. When equipped with general-purpose harnesses, they frequently produce physically implausible outputs, generating objects that interpenetrate, lack physical support, or move unnaturally. Such bare agents struggle to repair these errors because they default to scripting the full animation in one pass, making it difficult to verify their work and disentangle complex spatiotemporal constraints. Drawing on the practice of human animators, we introduce DyCraft, a system for animated 3D scene generation that breaks animation into steps that coding…
3D scene generationarticulated assetslong-horizon animationsphysical plausibilityDyCraft3D storyboardkey animation posesmotion authoring toolsspatiotemporal constraints
- Upvotes
- 4
- Authors
- 8
- Published
- Oct 29, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
DyCraft: An Agentic System for Long-Horizon 4D Scene Generation was first seen on Hugging Face · Daily papers on Nov 11, 2026. Since then it has appeared in 18 checks on 3 different days. Its best position was #23 of 30, reached on Nov 12, 11:28 UTC. It dropped off the list after Nov 13, 07:28 UTC.