用混合运动动态让风格化角色动画更自然流畅。
MikuDance: Animating Character Art with Mixed Motion Dynamics
- 分层建模角色与场景的动态运动，统一处理复杂动作。
- 通过自适应归一化注入全局场景运动，提升动画连贯性。
- 适合需要精细角色动作控制的动画创作者使用。
我们提出 MikuDance，一种基于扩散模型的动画生成框架，结合混合运动动态来驱动风格化角色艺术。该方法包含两项核心技术：混合运动建模与混合控制扩散，以解决角色动画中高动态运动与参考引导错位的问题。具体地，提出场景运动追踪策略，在像素级空间显式建模动态相机，实现角色与场景运动的统一建模。在此基础上，混合控制扩散隐式对齐不同角色的尺度与身体形状与运动引导，支持局部角色动作的灵活控制。随后引入运动自适应归一化模块，有效注入全局场景运动，为完整角色艺术动画提供支持。大量实验表明，MikuDance 在多种角色艺术与运动引导下均表现出优异的泛化能力与高质量动画生成效果，显著提升动作动态表现。
原文摘要 · Abstract (English)
We propose MikuDance, a diffusion-based pipeline incorporating mixed motion dynamics to animate stylized character art. MikuDance consists of two key techniques: Mixed Motion Modeling and Mixed-Control Diffusion, to address the challenges of high-dynamic motion and reference-guidance misalignment in character art animation. Specifically, a Scene Motion Tracking strategy is presented to explicitly model the dynamic camera in pixel-wise space, enabling unified character-scene motion modeling. Building on this, the Mixed-Control Diffusion implicitly aligns the scale and body shape of diverse characters with motion guidance, allowing flexible control of local character motion. Subsequently, a Motion-Adaptive Normalization module is incorporated to effectively inject global scene motion, paving the way for comprehensive character art animation. Through extensive experiments, we demonstrate the effectiveness and generalizability of MikuDance across various character art and motion guidance, consistently producing high-quality animations with remarkable motion dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。