Research map / Video / Video generation
MotionCharacter: Fine-Grained Motion Controllable Human Video Generation
Haopeng Fang, Di Qiu, Binjie Mao, He Tang
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 region-aware loss (ablation) | MotionCharacter · Unsplash-50 | Dynamic Degree: 0.355 -> 0.419 | Improved |
| add region-aware loss (ablation) | MotionCharacter · Unsplash-50 | Dover Score: 0.801 -> 0.860 | Improved |
| add region-aware loss (ablation) | MotionCharacter · Unsplash-50 | Face Similarity: 0.484 -> 0.500 | No clear effect |
| add ID-consistency loss (ablation) | MotionCharacter · Unsplash-50 | Face Similarity: 0.484 -> 0.588 | Improved |
| add ID-consistency loss to region-aware loss (ablation) | MotionCharacter · Unsplash-50 | Face Similarity: 0.500 -> 0.609 | Improved |
| add region-aware loss to ID-consistency loss (ablation) | MotionCharacter · Unsplash-50 | Dynamic Degree: 0.359 -> 0.449 | Improved |
| add Motion Control Module (ablation) | MotionCharacter · Unsplash-50 | Dynamic Degree: 0.245 -> 0.449 | Improved |
| add Motion Control Module (ablation) | MotionCharacter · Unsplash-50 | Face Similarity: 0.601 -> 0.609 | Mixed |
| use MotionCharacter instead of IPA-FaceID-PlusV2 | MotionCharacter · Unsplash-50 | Face Similarity: 0.617 -> 0.609 | Hurt |
| use MotionCharacter instead of ID-Animator | MotionCharacter · Unsplash-50 | Dynamic Degree: 0.433 -> 0.449 | Improved |
Closest papers by meaning
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · similarity 0.90)
- TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation (CVPR 2025 · similarity 0.90)
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.90)
- MMM: Generative Masked Motion Model (CVPR 2024 · similarity 0.90)
- HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation (CVPR 2025 · similarity 0.90)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.90)
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.
