MikuDance: Animating Character Art with Mixed Motion Dynamics
This work solves the problem of generating realistic animations for stylized characters, which is incremental as it builds on existing diffusion methods with novel techniques for motion modeling and control.
The paper tackles the problem of animating stylized character art by addressing high-dynamic motion and reference-guidance misalignment, resulting in a diffusion-based pipeline that produces high-quality animations with remarkable motion dynamics across various character art and motion guidance.
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.