Abstract: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.
| Comments: | Github Page:this https URL |
| Subjects: | Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.13857 [cs.GR] |
| (or arXiv:2605.13857v1 [cs.GR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13857 arXiv-issued DOI via DataCite |
Submission history
From: Dongxia Liu [view email]
[v1]
Wed, 8 Apr 2026 15:42:16 UTC (14,138 KB)