Research map / Video / Video generation
MikuDance: Animating Character Art with Mixed Motion Dynamics
Jiaxu Zhang, Xianfang Zeng, Xin Chen, Wei Zuo, Gang Yu, Zhigang Tu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add mixed-control architecture (MIX) (ablation) | MikuDance · MMD test set (100 videos) | FID: 27.315 -> 24.597 | Improved |
| add mixed-control architecture (MIX) (ablation) | MikuDance · MMD test set (100 videos) | FVD: 541.453 -> 502.380 | Improved |
| add Motion-Adaptive Normalization (MAN) (ablation) | MikuDance · MMD test set (100 videos) | FID: 24.985 -> 24.597 | Improved |
| add Motion-Adaptive Normalization (MAN) (ablation) | MikuDance · MMD test set (100 videos) | FVD: 509.342 -> 502.380 | Improved |
| add Scene Motion Tracking (SMT) (ablation) | MikuDance · MMD test set (100 videos) | FID: 25.472 -> 24.597 | Improved |
| add Scene Motion Tracking (SMT) (ablation) | MikuDance · MMD test set (100 videos) | FVD: 517.673 -> 502.380 | Improved |
| use SMT scene motion instead of Plucker embedding (ablation) | MikuDance · MMD test set (100 videos) | FID: 25.918 -> 24.597 | Improved |
| use SMT scene motion instead of optical flow (ablation) | MikuDance · MMD test set (100 videos) | FID: 26.141 -> 24.597 | Improved |
| use SMT scene motion instead of optical flow (ablation) | MikuDance · MMD test set (100 videos) | FVD: 505.533 -> 502.380 | Improved |
| use SMT scene motion instead of Plucker embedding (ablation) | MikuDance · MMD test set (100 videos) | FVD: 521.853 -> 502.380 | Improved |
| fine-tune Animate Anyone on the MMD video dataset | Animate Anyone · MMD test set (100 videos) | FID: 43.945 -> 28.833 | Improved |
| evaluate on foreground-only (background masked) | MikuDance · MMD test set, foreground-only | FID: 24.597 -> 14.835 | Improved |
Closest papers by meaning
- Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (CVPR 2024 · similarity 0.88)
- Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model (CVPR 2024 · similarity 0.87)
- AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models (CVPR 2025 · similarity 0.86)
- FlexiClip: Locality-Preserving Free-Form Character Animation (ICML 2025 · similarity 0.85)
- Animate-X: Universal Character Image Animation with Enhanced Motion Representation (ICLR 2025 · similarity 0.85)
- Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
