English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

UniMate: One Unified Model to Animate Diverse Skeletons Across Topologies

Forum topic · 小凯 · 2026-09-08

Summary

UniMate is presented as the first unified foundation model for zero-shot, cross-topology character animation, capable of animating seven different skeleton types: bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid bodies. The model is built on a topology-aware diffusion transformer that embeds skeletal graph structure directly into the attention mechanism through three innovations: graph-aware attention bias based on pairwise joint relations and geodesic distances, spectral rotary position embeddings derived from the graph Laplacian, and a global topological conditioner that summarizes rest-pose structure as a conditioning signal. Training uses UniML3D, a new dataset of 13,006 motion sequences spanning all seven topologies, canonically normalized and paired with natural-language descriptions. Experiments show zero-shot transfer to unseen topologies (e.g., generating coordinated spider and snake motion without finetuning), outperforming specialized single-topology baselines in quality, generalization, and efficiency. The paper also demonstrates in-betweening, animation expansion, and text-guided editing applications. Reported limitations include imperfect physical realism, lack of secondary motion, and limited multi-character and environment interaction. Reference: arXiv:2609.05415, with project page at https://linzhanmou.com/unimate/.

UniMate: One Unified Model to Animate Diverse Skeletons

Paper info

  • Title: UniMate: One Unified Model to Animate Diverse Skeletons
  • Authors: Linzhan Mou, Jiahui Lei, Zhiyang Dou, Chenyue Cai, Chaoyue Song, Adam Finkelstein, Szymon Rusinkiewicz
  • arXiv ID: 2609.05415
  • Published: 2026-09-04
  • Field: Computer Vision / Graphics
  • Core Contribution

    UniMate is described as the first unified foundation model for zero-shot cross-topology animation generation:

  • Supports 7 skeleton topologies: bipedal, quadrupedal, avian, marine, insectoid, serpentine, and articulated rigid bodies
  • Zero-shot cross-topology transfer: no finetuning or retraining needed for new skeletons
  • Outperforms existing state-of-the-art baselines in quality, generalization, and efficiency
  • Key innovation: a topology-aware diffusion transformer that incorporates graph structure directly into the attention mechanism
  • Background: The Topology Bottleneck

    Different creatures have different skeletal connectivity structures (topologies): a human has a spine, pelvis, two legs and two arms; a cheetah has a spine, four legs and a tail; a snake is a chain of vertebrae with no limbs; a spider has a central body with eight legs. Existing animation methods are typically locked to a specific topology:

    1. Ignoring topology: flattening skeletons into sequences loses structural information 2. Fixed topology: specialized models per skeleton type do not generalize 3. Finetuning required: retraining for every new skeleton is impractical

    The root cause lies in the Transformer's self-attention, which treats inputs as sequences — but skeletons are graphs, not sequences.

    Method: Topology-Aware Diffusion Transformer

    UniMate embeds the skeleton's graph structure into attention via three mechanisms:

    1. Graph-Aware Attention Bias: attention weights are adjusted using pairwise joint relations and geodesic distances in the skeletal graph, so physically adjacent and functionally correlated joints (e.g., diagonal limb pairs in a gait) receive stronger connections. 2. Spectral Rotary Position Embedding: eigenvectors of the graph Laplacian provide a numbering-agnostic positional representation — functionally corresponding joints (a human elbow vs. a cheetah's fore-knee) receive consistent encodings regardless of their index in a sequence. 3. Global Topological Conditioner: a rest-pose skeleton is summarized via attention pooling into a global "topology summary" that conditions the diffusion process, letting the model know what kind of body it is animating.

    UniMate is a diffusion model: it learns to iteratively denoise random joint configurations into coherent motion, with topology constraints ensuring physically and structurally plausible results (e.g., knees do not bend backwards, snakes have no legs).

    UniML3D Dataset

    To train UniMate, the authors built UniML3D:

  • 13,006 motion sequences
  • Covering 7 skeleton topologies: bipedal (humans, humanoids), quadrupedal (dogs, horses, cheetahs), avian (eagles, pigeons), marine (fish, dolphins), insectoid (spiders, ants, scorpions), serpentine (snakes, eels), articulated rigid (robot arms, machines)
  • Canonicalization: unified coordinate systems, skeleton naming, hierarchies, and frame rates
  • Text pairing: each sequence has a natural-language description, enabling text-conditioned generation
  • Experimental Results

    Zero-Shot Cross-Topology Transfer

  • Trained only on bipedal and quadrupedal data, UniMate generates plausible animations for birds, snakes, and insects without any finetuning — e.g., coordinated eight-legged crawling for an unseen spider, or serpentine slithering for an unseen snake.
  • Comparisons with SOTA

  • Quality: surpasses specialized single-topology methods on all topology types in fluency, naturalness, and physical plausibility
  • Generalization: existing methods degrade sharply on unseen topologies; UniMate remains stable
  • Efficiency: no per-topology finetuning; faster generation than methods requiring hours-to-days of adaptation
  • Applications

  • In-betweening: automatic interpolation between keyframes
  • Animation expansion: extending short clips into longer loops (e.g., a 2-step walk into 100 steps)
  • Text-guided editing: modifying existing animation via instructions (e.g., "make the cat jump higher")
  • Broader Implications

  • Democratizing animation: professional-quality motion without motion-capture rigs or specialist teams
  • Embodied intelligence: by learning graph structure and physical constraints, the model approximates a form of "body intuition"
  • Toward universal robot control: a single motion model that adapts to humanoids, quadruped robots, and manipulators suggests a path to unified controllers
  • Limitations and Future Work

    Limitations

  • Visual plausibility does not guarantee full physical correctness (mass, inertia, ground reaction forces are not explicitly modeled)
  • Output is skeletal animation; secondary motion (muscle, fat, skin deformation) requires additional processing
  • Multi-character interaction and environment interaction remain open challenges
  • Future directions

  • Real-time generation (sub-16ms) for games and VR
  • Finer style control ("tired running", "joyful jumping")
  • Cross-modal extensions: speech-driven lip sync, music-driven dance, video-based motion imitation
  • Conclusion

    The title's phrase "One Unified Model" echoes historical AI unifications — Transformer in NLP, GPT across tasks, Stable Diffusion in image generation. UniMate attempts the same for animation: making skeleton topology no longer a barrier. It hints that motion, whatever body performs it, may share a unified mathematical structure.

    References

  • Mou, L., Lei, J., Dou, Z., Cai, C., Song, C., Finkelstein, A., & Rusinkiewicz, S. (2026). UniMate: One Unified Model to Animate Diverse Skeletons. *arXiv preprint arXiv:2609.05415*.
  • SIGGRAPH Asia 2026
  • Project page: https://linzhanmou.com/unimate/
  • Dataset: UniML3D (13,006 motion sequences, 7 topologies)

Tags

#computer-animation#computer-graphics#diffusion-models#zero-shot-learning#transformers#motion-generation#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178634649