demo.mp4
TL;DR: MoZoo synthesizes high-fidelity animal dynamics from coarse meshes using Role-Aware RoPE and Asymmetric Decoupled Attention, achieving superior fur and muscle simulation across diverse species.
The creation of cinematic-quality animal effects necessitates the precise modeling of muscle and fur dynamics, a process that remains both labor-intensive and computationally expensive within traditional production workflows. While generative diffusion models have shown promise in diverse artistic workflows, their capacity for high-fidelity animal simulation remains largely unexploited. We present MoZoo, a generative dynamics solver that bypasses conventional refinement to synthesize high-fidelity animal videos from coarse meshes under multimodal guidance. We propose Role-Aware RoPE (RAR-RoPE) which employs role-based index remapping to synchronize motion alignment while decoupling reference information via fixed temporal offsets. Complementing this, Asymmetric Decoupled Attention partitions the latent sequence to enforce a unidirectional information flow, effectively preventing feature interference and improving computational efficiency. To address the scarcity of high-quality training data, we introduce MoZoo-Data, a synthetic-to-real pipeline that leverages a rendering engine and an inverse mapping approach to construct a large-scale dataset of paired sequences. Furthermore, we establish MoZooBench, a comprehensive benchmark with 120 mesh-video pairs. Experimental results demonstrate that MoZoo achieves high-fidelity fur simulation across diverse animal skeletons and layouts, preserving superior temporal and structural consistency.
- [2026.4.04] Paper and local demo code released.
Visit our Project Page to view complete demo videos and visual results.
If you're interested in this project, please give us a Star ⭐ to receive timely open-source notifications!
Please leave us a star 🌟 and cite our repo if you find our work helpful.
@misc{liu2026mozoounleashingvideodiffusionpower,
title={MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation},
author={Dongxia Liu and Jie Ma and Xiaochen Yang and Jiancheng Zhang and Bin Xia and Zhehan Kan and Nisha Huang and Jun Liang and Wenming Yang and Jin Li},
year={2026},
eprint={2605.13857},
archivePrefix={arXiv},
primaryClass={cs.GR},
url={https://arxiv.org/abs/2605.13857},
}