Research map / Video / Video generation
DragVideo: Interactive Drag-style Video Editing
Yufan Deng, Ruida WANG, Yuhao ZHANG, Yu-Wing Tai, Chi-Keung Tang
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 |
|---|---|---|---|
| use DragVideo instead of per-frame DragDiffusion extension | drag-style video editing · evaluation set of 20 sample outputs | RAFT optical flow (jitter): 3.3807 -> 2.3780 | Improved |
| use DragVideo instead of per-frame DragDiffusion extension | drag-style video editing · evaluation set of 20 sample outputs | CLIP consistency: 0.9833 -> 0.9893 | Improved |
| use DragVideo instead of Tune-A-Video | drag-style video editing · evaluation set of 20 sample outputs | FVD diff to original: 2682.37 -> 397.43 | Improved |
| use DragVideo instead of per-frame DragDiffusion extension | drag-style video editing · evaluation set of 20 sample outputs | FVD diff to original: 400.89 -> 397.43 | No clear effect |
| add sample-specific LoRA (ablation) | DragVideo · qualitative ablation | style and identity preservation | Improved |
| add Mutual Self-Attention denoising (ablation) | DragVideo · qualitative ablation | output quality | Improved |
| run DragVideo versus baselines in user study | DragVideo · user study, 53 subjects | satisfaction score (1-10) 98% CI: effectiveness CI (7.47, 8.51); consistency CI (7.74, 8.96) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Tune-A-Video — Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation (ICCV 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ReVideo: Remake a Video with Motion and Content Control (NeurIPS 2024 · similarity 0.88)
- Transforming Image Editors into Video Editors (NeurIPS 2026 · similarity 0.87)
- GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models (ICLR 2025 · similarity 0.87)
- LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos (ICML 2025 · similarity 0.87)
- SketchVideo: Sketch-based Video Generation and Editing (CVPR 2025 · similarity 0.87)
- FADE: Frequency-Aware Diffusion Model Factorization for Video Editing (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.
