Topology-Agnostic Animal Motion Generation from Text Prompt

TL;DR

This paper introduces OmniZoo, a large-scale animal motion dataset, and a novel topology-agnostic generative framework that produces text-driven, physically plausible animal motions across diverse skeletal structures.

Contribution

The work presents a new dataset and a generalized autoregressive model with a topology-aware embedding for flexible, text-driven animal motion generation across different skeleton topologies.

Findings

Successfully generates coherent animal motions from text prompts.

Enables cross-species motion style transfer.

Handles arbitrary skeletal topologies with high fidelity.

Abstract

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.