发表机构
University of Illinois Urbana-Champaign; University of Pennsylvania; Stanford University; University of Cambridge（伊利诺伊大学厄巴纳-香槟分校; 宾夕法尼亚大学; 斯坦福大学; 剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对动物动作数据稀缺的问题，提出Kirin框架，构建首个四足动物视频-文本-动作对齐大规模数据集AiM3D，开发双条件动作生成模型，实现可渲染动画动物的自动生成。
AI 中文摘要
理解动物动作是建模动物行为和生物力学的基础，但由于高质量动作数据稀缺，该领域的进展远落后于人类动作研究。虽然人类动作可在受控环境中捕获，但对大多数动物物种而言不具可行性，导致数据集规模小、领域受限，限制了动画等下游应用。为应对这一挑战，我们引入Kirin框架，该框架可从视频重建动作、大规模学习动作先验，并生成可直接应用于动画资产的逼真动作。利用大量野外动物视频，我们重建3D动作序列并将其与文本配对，创建了AiM3D——首个提供四足动物对齐的视频-文本-动作元组的大规模数据集。基于该数据集，我们开发了视觉引导的动作生成模型，该模型以文本和图像为条件，指导不同动物物种的逼真动作生成。最后，通过利用现成的图像转3D模型，我们使用生成的动作自动绑定并动画化3D网格，生成可直接渲染的动画动物。我们的数据集和框架共同为大规模、文本和图像条件下的动物动作生成与动画奠定了新基础。项目页面：this https URL。
英文摘要
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/.
CommentsECCV 2026
