Topology-Agnostic Animal Motion Generation from Text Prompt
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915668429897728 |
|---|---|
| author | Chen, Keyi Sun, Mingze Liu, Zhenyu Chen, Zhangquan Huang, Ruqi |
| author_facet | Chen, Keyi Sun, Mingze Liu, Zhenyu Chen, Zhangquan Huang, Ruqi |
| contents | Motion generation is fundamental to computer animation and widely used across entertainment, robotics, and virtual environments. While recent methods achieve impressive results, most rely on fixed skeletal templates, which prevent them from generalizing to skeletons with different or perturbed topologies. We address the core limitation of current motion generation methods - the combined lack of large-scale heterogeneous animal motion data and unified generative frameworks capable of jointly modeling arbitrary skeletal topologies and textual conditions. To this end, we introduce OmniZoo, a large-scale animal motion dataset spanning 140 species and 32,979 sequences, enriched with multimodal annotations. Building on OmniZoo, we propose a generalized autoregressive motion generation framework capable of producing text-driven motions for arbitrary skeletal topologies. Central to our model is a Topology-aware Skeleton Embedding Module that encodes geometric and structural properties of any skeleton into a shared token space, enabling seamless fusion with textual semantics. Given a text prompt and a target skeleton, our method generates temporally coherent, physically plausible, and semantically aligned motions, and further enables cross-species motion style transfer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10352 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Topology-Agnostic Animal Motion Generation from Text Prompt Chen, Keyi Sun, Mingze Liu, Zhenyu Chen, Zhangquan Huang, Ruqi Computer Vision and Pattern Recognition Motion generation is fundamental to computer animation and widely used across entertainment, robotics, and virtual environments. While recent methods achieve impressive results, most rely on fixed skeletal templates, which prevent them from generalizing to skeletons with different or perturbed topologies. We address the core limitation of current motion generation methods - the combined lack of large-scale heterogeneous animal motion data and unified generative frameworks capable of jointly modeling arbitrary skeletal topologies and textual conditions. To this end, we introduce OmniZoo, a large-scale animal motion dataset spanning 140 species and 32,979 sequences, enriched with multimodal annotations. Building on OmniZoo, we propose a generalized autoregressive motion generation framework capable of producing text-driven motions for arbitrary skeletal topologies. Central to our model is a Topology-aware Skeleton Embedding Module that encodes geometric and structural properties of any skeleton into a shared token space, enabling seamless fusion with textual semantics. Given a text prompt and a target skeleton, our method generates temporally coherent, physically plausible, and semantically aligned motions, and further enables cross-species motion style transfer. |
| title | Topology-Agnostic Animal Motion Generation from Text Prompt |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.10352 |