UniMate：用於驅動多種骨架的統一模型

摘要

近來自動綁定的進展使得大規模產出動畫就緒的 3D 資產成為可能，然而生成驅動這些資產的動作仍然是瓶頸。現有的學習式動畫器受到拓撲限制：它們依賴類別特定的模板，或在推論時需要逐骨架微調與參考動作。我們提出 UniMate，一個統一基礎模型，能夠從綁定好的 3D 資產與文字提示，為任意骨架合成關節動作，無需測試時最佳化或逐骨架重新訓練。UniMate 引入了拓撲感知擴散 Transformer，透過三種機制將骨架拓撲整合至注意力中：(1) 由成對關節關係與測地距離產生的圖感知注意力偏置；(2) 頻譜旋轉位置嵌入，透過圖拉普拉斯矩陣將 RoPE 推廣至任意運動學樹；(3) 從靜止姿勢骨架進行注意力池化的全域拓撲條件器。我們亦整理了 UniML3D 資料集，內含 13,006 筆動作序列，涵蓋雙足、四足、鳥類、海洋、昆蟲、蛇形與關節式剛體物件，並具備統一的標準化處理與文字配對。在此資料集上訓練的 UniMate，在品質、泛化能力與效率上均優於當前最佳基準方法，並支援零樣本跨拓撲遷移、補間動畫、擴展與文字引導編輯。我們的專案頁面位於 https://linzhanmou.com/unimate/。

English

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/.