Kirin: Animal Motion Generation from In-the-Wild Video

Hugging Face Daily Papers Papers
animal-motion 3d-reconstruction motion-generation dataset text-conditioned image-conditioned animation

Summary

Kirin reconstructs 3D animal motion from in-the-wild videos to create the AiM3D dataset and generate text- and image-conditioned motion for animating 3D meshes.

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/.
Original Article
View Cached Full Text

Cached at: 09/03/26, 03:50 AM

Paper page - Kirin: Animal Motion Generation from In-the-Wild Video

Source: https://huggingface.co/papers/2609.01823

Abstract

Kirin reconstructs 3D animal motion from video to build a large-scale dataset and generate text- and image-conditioned motion for animating 3D meshes.

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, learnsmotion priorsat 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 forquadruped animals. Building on this dataset, we develop avisual-guided motion generationmodel 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/.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2609\.01823

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.01823 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.01823 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.01823 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles