Research map / Video / Video generation
SMooDi: Stylized Motion Diffusion Model
Lei Zhong, Yiming Xie, Varun Jampani, Deqing Sun, Huaizu Jiang
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 cycle prior-preservation loss (ablation) | SMooDi · Stylized text2motion | FID: 2.046 -> 1.609 | Improved |
| add content prior-preservation loss (with cycle loss) (ablation) | SMooDi · Stylized text2motion | FID: 5.996 -> 2.046 | Improved |
| add classifier-based style guidance (ablation) | SMooDi · Stylized text2motion | SRA (%): 20.245 -> 72.418 | Improved |
| add classifier-based style guidance (ablation) | SMooDi · Stylized text2motion | FID: 1.050 -> 1.609 | Hurt |
| add content-aware style adaptor (ablation) | SMooDi · Stylized text2motion | FID: 2.984 -> 1.609 | Improved |
| generate stylized motion with SMooDi instead of MLD plus style transfer | SMooDi · Stylized text2motion | SRA: 63.769 -> 72.418 | Improved |
| describe style in text via ChatGPT instead of a style motion | MLD · Stylized text2motion | SRA: 72.418 -> 4.819 | Hurt |
| use SMooDi via DDIM inversion for style transfer instead of dedicated transfer methods | SMooDi · Xia dataset style transfer | SRA (%): 67.778 -> 61.111 (SRA), 25.556 -> 45.555 (CRA) | Mixed |
Closest papers by meaning
- StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion (ICCV 2025 · similarity 0.90)
- Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model (CVPR 2024 · similarity 0.88)
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning (ICLR 2024 · similarity 0.86)
- Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model (AAAI 2024 · similarity 0.86)
- Generative Human Motion Stylization in Latent Space (ICLR 2024 · similarity 0.86)
- Scalable Motion Style Transfer with Constrained Diffusion Generation (AAAI 2024 · 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.
