Research map / Video / Video generation
Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!
Junbao Zhou, Yuan Zhou, Kesen Zhao, Qingshan Xu, Beier Zhu, Richang Hong, Hanwang Zhang
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 |
|---|---|---|---|
| increase drag latent-optimization iterations from 0 to 4 (ablation) | DragStream · REVEL streaming drag | ObjMC: 90.39 -> 23.05 | Improved |
| increase iterations from 0 to 4 (ablation) | DragStream · REVEL streaming drag | DAI: 0.133 -> 0.051 | Improved |
| increase iterations from 0 to 4 (ablation) | DragStream · REVEL streaming drag | runtime per frame: 0.17s -> 0.30s | Hurt |
| increase iterations from 3 to 4 (ablation) | DragStream · REVEL streaming drag | ObjMC: 24.55 -> 23.05 | Improved |
| add SFSO (spatial-frequency selective optimization) on top of ADSR (ablation) | DragStream · REVEL streaming drag | video quality and drag precision | Improved |
| add ADSR (adaptive distribution self-rectification) (ablation) | DragStream · REVEL streaming drag | ObjMC, DAI, FVD, FID | Improved |
| use switchable cutoff frequency instead of fixed small or large (ablation) | SFS in DragStream · REVEL streaming drag | video quality | Improved |
| use full SFSO instead of CSS or SFS alone (ablation) | DragStream · REVEL streaming drag | video quality | Improved |
| use DragStream instead of SG-I2V and DragVideo | adapted baselines · REVEL streaming drag | FID, FVD, ObjMC, DAI | Improved |
Closest papers by meaning
- DragVideo: Interactive Drag-style Video Editing (ECCV 2024 · similarity 0.90)
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models (CVPR 2025 · similarity 0.86)
- AdaState: Self-Evolving Anchors for Streaming Video Generation (NeurIPS 2026 · similarity 0.85)
- Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model (ICLR 2025 · similarity 0.85)
- ReVideo: Remake a Video with Motion and Content Control (NeurIPS 2024 · similarity 0.85)
- FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation (NeurIPS 2025 · 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.
