Research map / 3D vision / 3D generation
MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion
Yikun Ma, Yiqing Li, Jiawei Wu, Xing Luo, Zhi Jin
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 DDIM inversion substitution (ablation) | MotionDiff · ScanNet200 ablation | MPA: 9.5 -> 6.8 | Improved |
| add DDIM inversion substitution (ablation) | MotionDiff · ScanNet200 ablation | MVC: 28.96 -> 34.92 | Improved |
| add DDIM inversion substitution (ablation) | MotionDiff · ScanNet200 ablation | ATF: 5.6 -> 5.1 | Improved |
| add FGS motion prior (ablation) | MotionDiff · ScanNet200 ablation | ATF: 10.2 -> 5.1 | Improved |
| add FGS motion prior (ablation) | MotionDiff · ScanNet200 ablation | MPA: 9.4 -> 6.8 | Improved |
| add FGS motion prior (ablation) | MotionDiff · ScanNet200 ablation | MVC: 32.14 -> 34.92 | Improved |
| add LSF latent fusion strategy (ablation) | MotionDiff · ScanNet200 ablation | MPA: 7.7 -> 6.8 | Improved |
| add LSF latent fusion strategy (ablation) | MotionDiff · ScanNet200 ablation | ATF: 5.1 -> 5.1 | No clear effect |
| add LSF latent fusion strategy (ablation) | MotionDiff · ScanNet200 ablation | MVC: 31.79 -> 34.92 | Improved |
| apply LSF in latent space instead of image space (ablation) | MotionDiff · ScanNet200 ablation | ATF: 7.5 -> 5.1 | Improved |
| apply LSF in latent space instead of image space (ablation) | MotionDiff · ScanNet200 ablation | MVC: 30.23 -> 34.92 | Improved |
| add BGC background grid constraint (ablation) | MotionDiff · ScanNet200 ablation | MPA: 7.2 -> 6.8 | Improved |
Closest papers by meaning
- Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators (ICLR 2024 · similarity 0.89)
- DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing (CVPR 2024 · similarity 0.87)
- Dynamic Motion Blending for Versatile Motion Editing (CVPR 2025 · similarity 0.87)
- MotionCraft: Physics-Based Zero-Shot Video Generation (NeurIPS 2024 · similarity 0.87)
- CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion (CVPR 2025 · similarity 0.87)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.86)
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.
