MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation

TL;DR

MoZoo introduces a novel generative dynamics solver for high-fidelity animal fur and muscle simulation, leveraging multimodal guidance, role-aware synchronization, and synthetic data to improve realism and efficiency.

Contribution

The paper presents MoZoo, a new approach combining role-aware synchronization, asymmetric attention, and synthetic data pipelines for realistic animal simulation.

Findings

MoZoo achieves high-fidelity fur and muscle simulation across various animals.

The method maintains superior temporal and structural consistency.

MoZoo outperforms existing techniques in realism and computational efficiency.

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.