Research map / Video / Video generation
Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion
Chen-Chieh Liao, YICHEN PENG, YIYI CAI, Yûi Ono, Hiroki Hanaoka, Erwin Wu, Hideki Koike, Shuichi Kurabayashi
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 linearity loss L_lin (ablation) | Motion Style Slider · PerMo | FMD: 0.605 -> 0.531 | Improved |
| add linearity loss L_lin (ablation) | Motion Style Slider · PerMo | SRA: 0.06 -> 0.14 | Improved |
| add linearity loss L_lin (ablation) | Motion Style Slider · PerMo | CRA: 0.54 -> 0.70 | Improved |
| add monotonicity loss L_mono (ablation) | Motion Style Slider · PerMo | SRA: 0.04 -> 0.14 | Improved |
| add monotonicity loss L_mono (ablation) | Motion Style Slider · PerMo | CRA: 0.56 -> 0.70 | Improved |
| add monotonicity loss L_mono (ablation) | Motion Style Slider · PerMo | MonoViol: 0.03 -> 0.03 | No clear effect |
| use instance direction instead of prototype direction (ablation) | Motion Style Slider · PerMo | LinErr: 0.513 -> 0.421 | Improved |
| use instance direction instead of hybrid direction (ablation) | Motion Style Slider · PerMo | SRA: 0.12 -> 0.14 | Improved |
| use instance direction instead of prototype direction (ablation) | Motion Style Slider · PerMo | CRA: 0.60 -> 0.70 | Improved |
| use Motion Style Slider instead of MCM-LDM | style transfer · PerMo/Bandai-Namco/Xia average | FMD: 0.381 -> 0.457 | Hurt |
| use Motion Style Slider instead of MCM-LDM | style transfer · PerMo/Bandai-Namco/Xia average | MonoViol: 0.11 -> 0.05 | Improved |
| use Motion Style Slider instead of MCM-LDM | style transfer · Xia | MonoViol: 0.05 -> 0.07 | Hurt |
Closest papers by meaning
- Scalable Motion Style Transfer with Constrained Diffusion Generation (AAAI 2024 · similarity 0.90)
- Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model (CVPR 2024 · similarity 0.89)
- Generative Human Motion Stylization in Latent Space (ICLR 2024 · similarity 0.88)
- MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation (AAAI 2024 · similarity 0.87)
- Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis (AAAI 2024 · similarity 0.87)
- StyleMaster: Stylize Your Video with Artistic Generation and Translation (CVPR 2025 · similarity 0.87)
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.
