UniMate: one unified model animates any skeleton topology, SIGGRAPH Asia paper
andrew_n_carr · x · 2026-09-08
UniMate (SIGGRAPH Asia 2026, Princeton et al.) is a unified foundation model that animates rigged 3D assets with arbitrary skeletal topologies from a text prompt — no test-time optimization or per-skeleton fine-tuning.
Key ideas:
- Topology-aware diffusion transformer integrating skeleton structure via graph-aware attention bias (pairwise joint relations + geodesic distances), a spectral rotary position embedding generalizing RoPE to arbitrary kinematic trees via the graph Laplacian, and a global topological conditioner pooled from the rest-pose skeleton
- UniML3D dataset: 13,006 motion sequences spanning bipedal, quadrupedal, avian, marine, insectoid, serpentine and articulated rigid bodies, with unified canonicalization and text pairing
It outperforms SOTA baselines in quality, generalization and efficiency, and supports zero-shot cross-topology transfer, in-betweening, expansion and text-guided editing. Author andrewncarr highlights editing part of a motion while keeping the rest fixed; some foot sliding remains.
Related event: Princeton Open-Sources UniMate: One Model Animates Any Skeleton(2 posts)→
More from Multimodal
- FLUX.2 Klein Drifts Hard on Character Expressions While Free Gemini Holds Likeness — wacomlover · 2026-09-11
- Tencent Hunyuan releases AuK code and weights on GitHub with ComfyUI and fine-tuning support — aigclink · 2026-09-11
- Creator turns Bahamut vs Tiamat rivalry into an AI cinematic battle with Midjourney, GPT Image 2 and Seedance — azed_ai · 2026-09-11
- invideo launches AI agent-powered editor to automate repetitive editing tasks — azed_ai · 2026-09-11
- fable 5.1 recreates The Starry Night with 256,157 JavaScript brush strokes — cedric_chee · 2026-09-11
- GPT-6 Astra + Hyper3D Rodin MCP Generates 3D Assets in One Agent Flow — ahuja_priyank · 2026-09-11