Search papers, labs, and topics across Lattice.
UniMate removes the long-standing topology bottleneck in 3D animation by introducing a unified foundation model capable of synthesizing text-driven motion across arbitrary skeletons without per-asset fine-tuning or test-time optimization. The architecture employs a topology-aware diffusion transformer that injects skeletal structure directly into attention via geodesic graph biases, a graph-Laplacian spectral rotary position embedding (RoPE), and rest-pose topological conditioning, trained on a new 13,006-sequence multi-species dataset. Consequently, the model outperforms category-specific baselines in generation quality while natively supporting zero-shot cross-topology transfer, in-betweening, and editing across morphologically distinct kinematic trees.
Motion generation is no longer bound to fixed human templates: a single diffusion model can now animate arbitrary skeletal topologies鈥攆rom serpents and insects to bipeds鈥攄irectly from text in zero-shot fashion.
Recent 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. We present UniMate, 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 retraining. UniMate introduces a topology-aware diffusion transformer, which integrates skeletal topology into attention via three mechanisms: (1) a graph-aware attention bias from pairwise joint relations and geodesic distances; (2) a spectral rotary position embedding generalizing RoPE to arbitrary kinematic trees via the graph Laplacian; and (3) a global topological conditioner attention-pooled from the rest-pose skeleton. We also curate UniML3D, 13,006 motion sequences spanning bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid objects with unified canonicalization and text pairing. Trained on this dataset, UniMate outperforms state-of-the-art baselines in quality, generalization, and efficiency, and supports zero-shot cross-topology transfer, in-betweening, expansion, and text-guided editing. Our project page is available at https://linzhanmou.com/unimate/.
