Research map / Video / Video generation
Click To Move: Controlling Video Generation With Sparse Motion
Pierfrancesco Ardino, Marco De Nadai, Bruno Lepri, Elisa Ricci, Stéphane Lathuilière
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 GCN-based motion estimation module (ablation) | C2M · Cityscapes | FVD: 369 -> 288 | Improved |
| add GCN-based motion estimation module (ablation) | C2M · Cityscapes | NDE: 1.42 -> 1.01 | Improved |
| add GCN-based motion estimation module (ablation) | C2M · Cityscapes | Acc: 0.70 -> 0.84 | Improved |
| add object interaction edges in GCN (ablation) | C2M · Cityscapes | FVD: 375 -> 288 | Improved |
| add object interaction edges in GCN (ablation) | C2M · Cityscapes | NDE: 1.38 -> 1.01 | No clear effect |
| add optical flow supervision (ablation) | C2M · Cityscapes | FVD: 301 -> 288 | Improved |
| add optical flow supervision (ablation) | C2M · Cityscapes | NDE: 1.13 -> 1.01 | Improved |
| add optical flow supervision (ablation) | C2M · Cityscapes | Acc: 0.84 -> 0.84 | No clear effect |
| give baseline user motion input (Sheng*) (ablation) | Sheng et al. · Cityscapes (Oracle N=1) | NDE: 2.11 -> 2.12 | Mixed |
| give baseline user motion input (Sheng*) (ablation) | Sheng et al. · Cityscapes (Oracle N=1) | FVD: 373 -> 498 | Hurt |
Closest papers by meaning
- Motion Prompting: Controlling Video Generation with Motion Trajectories (CVPR 2025 · similarity 0.89)
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · similarity 0.89)
- Follow-Your-Click: Open-domain Regional Image Animation via Motion Prompts (AAAI 2025 · similarity 0.88)
- Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation (AAAI 2024 · similarity 0.88)
- MotionPro: A Precise Motion Controller for Image-to-Video Generation (CVPR 2025 · similarity 0.87)
- MotionClone: Training-Free Motion Cloning for Controllable Video Generation (ICLR 2025 · 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.
