| title | Kirin: Animal Motion Generation from In-the-Wild Video |
|---|---|
| authors | Brian Nlong Zhao, Zhuoyang Pan, James M. Rehg, Jiajun Wu, Shangzhe Wu |
| date | 2026-09-01 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.01823 |
| upvotes | 3 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Understanding animal motion is fundamental to modeling animal behavior and biomechanics, yet progress in this area lags far behind human motion research due to the scarcity of high-quality motion data. While human motion can be captured in controlled environments, it is impractical for most animal species, resulting in small, domain-limited datasets that restrict downstream applications such as animation. To address this challenge, we introduce Kirin, a framework that reconstructs motion from video, learns motion priors at scale, and generates realistic motion that can be directly applied to animated assets. Using large collections of in-the-wild animal videos, we reconstruct 3D motion sequences and pair them with captions to create AiM3D, the first large-scale dataset offering aligned video-text-motion tuples for quadruped animals. Building on this dataset, we develop a visual-guided motion generation model that conditions on both text and image to guide the generation of realistic motion across diverse animal species. Finally, by leveraging an off-the-shelf image-to-3D model, we automatically rig and animate 3D meshes using generated motion, producing ready-to-render animated animals. Together, our dataset and framework establish a new foundation for large-scale, text and image conditioned animal motion generation and animation. Project page: https://kirin-ani.github.io/. |
cite
@misc{zhao2026kirin,
title={Kirin: Animal Motion Generation from In-the-Wild Video},
author={Brian Nlong Zhao and Zhuoyang Pan and James M. Rehg and Jiajun Wu and Shangzhe Wu},
year={2026},
eprint={2609.01823},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.01823}
}