UniMate: One Unified Model to Animate Diverse Skeletons
Researchers introduce UniMate, a topology-aware diffusion transformer generating text-driven motion for arbitrary 3D skeletons without per-skeleton retraining.
UniMate is a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text prompt, with no test-time optimization or per-skeleton fine-tuning. It uses a topology-aware diffusion transformer combining graph-aware attention bias, a spectral rotary position embedding generalizing RoPE via the graph Laplacian, and a rest-pose topological conditioner. Trained on UniML3D, a curated set of 13,006 motion sequences spanning bipedal to serpentine skeletons, it outperforms state-of-the-art baselines and supports zero-shot cross-topology transfer, in-betweening, and text-guided editing.
- Integrates skeletal topology into attention via graph Laplacian-based RoPE generalization
- UniML3D dataset spans 13,006 motion sequences across diverse topology families
- Supports zero-shot cross-topology transfer, in-betweening, and text-guided editing
From the original article
1 min read at arxiv.orgRecent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference.
By Linzhan Mou · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.