Research map / Video / Video generation
EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
Yehonathan Litman, Shikun Liu, Dario Seyb, Nicholas Milef, Yang Zhou, Carl Marshall, Shubham Tulsiani, Caleb Leak
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 |
|---|---|---|---|
| fine-tune the local encoder with LoRA (vs naive token dropping) (ablation) | EditCtrl · VPBench-Edit | PSNR: 23.24 -> 23.80 | Improved |
| add global context embedder (ablation) | EditCtrl local encoder · VPBench-Edit | PSNR: 23.80 -> 24.16 | Improved |
| add global context embedder (ablation) | EditCtrl local encoder · VPBench-Edit | throughput (FPS): 4.90 -> 4.67 | Hurt |
| restrict computation to masked tokens via local encoder and global embedder | VACE 1.3B · VPBench-Edit | PFLOPS: 76.31 -> 17.42 | Improved |
| restrict computation to masked tokens | VACE 1.3B · VPBench-Edit | throughput (FPS): 0.66 -> 4.67 | Improved |
| restrict computation to masked tokens | VACE 14B · VPBench-Edit | PSNR: 24.02 -> 24.37 | Improved |
| restrict computation to masked tokens | VACE 1.3B · VPBench-Inp | PSNR: 22.62 -> 23.17 | Improved |
| restrict computation to masked tokens | VACE 14B · DAVIS inpainting | PSNR: 26.12 -> 25.89 | Hurt |
| restrict computation to masked tokens | VACE 1.3B · DAVIS inpainting | PSNR: 25.75 -> 25.44 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- ProPainter — ProPainter: Improving Propagation and Transformer for Video Inpainting (ICCV 2023) · better on 1 of 2 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
- CCEdit: Creative and Controllable Video Editing via Diffusion Models (CVPR 2024 · similarity 0.88)
- MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers (CVPR 2024 · similarity 0.88)
- VideoDirector: Precise Video Editing via Text-to-Video Models (CVPR 2025 · similarity 0.87)
- Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists (NeurIPS 2025 · similarity 0.87)
- VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling (NeurIPS 2026 · similarity 0.87)
- VicEdit: Learning to Edit Videos from Visual In-Context Examples (NeurIPS 2026 · 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.
