Research map / Video / Video generation
Controllable Video Generation With Sparse Trajectories
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use the full two-stage model instead of Beyond MSE | video generation from one frame and sparse trajectories · KITTI | PSNR: 10.86 -> 20.88 | Helped |
| use the full two-stage model instead of Beyond MSE | video generation from one frame and sparse trajectories · KITTI | SSIM: 0.452 -> 0.766 | Helped |
| use the full two-stage model instead of Beyond MSE | video generation from one frame and sparse trajectories · Robot Pushing | PSNR: 23.30 -> 34.17 | Helped |
| use the full two-stage model instead of Beyond MSE | video generation from one frame and sparse trajectories · Robot Pushing | SSIM: 0.886 -> 0.973 | Helped |
| use the full two-stage model instead of Beyond MSE | video generation from one frame and sparse trajectories · UCF-101 | PSNR: 18.64 -> 28.13 | Helped |
| use the full two-stage model instead of Beyond MSE | video generation from one frame and sparse trajectories · UCF-101 | SSIM: 0.830 -> 0.934 | Helped |
| add pixel hallucination to flow completion (ablation) | video generation model · Robot Pushing | human preference: 10.9 -> 87.2 | Helped |
| add pixel hallucination to flow completion (ablation) | video generation model · KITTI | human preference: 11.4 -> 86.2 | Helped |
| add pixel hallucination to flow completion (ablation) | video generation model · UCF-101 | human preference: 17.8 -> 79.0 | Helped |
| add sparse-to-dense flow completion to hallucination (ablation) | video generation model · Robot Pushing | human preference: 1.9 -> 87.2 | Helped |
| add sparse-to-dense flow completion to hallucination (ablation) | video generation model · KITTI | human preference: 2.4 -> 86.2 | Helped |
| add sparse-to-dense flow completion to hallucination (ablation) | video generation model · UCF-101 | human preference: 3.2 -> 79.0 | Helped |
Closest papers by meaning
- Motion Prompting: Controlling Video Generation with Motion Trajectories (CVPR 2025 · similarity 0.90)
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · similarity 0.90)
- IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot Manner (CVPR 2025 · similarity 0.88)
- Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation (AAAI 2024 · similarity 0.88)
- SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation (ICLR 2025 · similarity 0.88)
- MotionPro: A Precise Motion Controller for Image-to-Video Generation (CVPR 2025 · similarity 0.88)
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.