Research map / Video / Video generation
StreamGVE: Training-Free Video Editing via Few-Step Streaming Video Generation
Guanlong Jiao, Chenyangguang Zhang, Jia Xian, Zewei Zhang, Renjie Liao
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 cross-attention boosting (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | FiVE-Acc: 39.05 -> 51.94 | Improved |
| add cross-attention boosting (ablation) | StreamEdit (LongLive) · FiVE-Bench | FiVE-Acc: 46.46 -> 55.04 | Improved |
| add cross-attention boosting (ablation) | StreamEdit (LongLive) + first frame · FiVE-Bench | FiVE-Acc: 54.78 -> 61.19 | Improved |
| add cross-attention boosting (ablation) | StreamEdit (Self Forcing) + first frame · FiVE-Bench | FiVE-Acc: 56.29 -> 58.64 | Improved |
| add cross-attention boosting (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | PSNR: 28.99 -> 28.47 | Hurt |
| increase boost scale omega from 2 to 5 (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | FiVE-Acc: 46.46 -> 52.52 | Improved |
| increase boost scale omega from 2 to 5 (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | PSNR: 28.85 -> 28.33 | Hurt |
| increase blending exponent rho from 0 to 3 (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | FiVE-Acc: 25.92 -> 57.99 | Improved |
| increase blending exponent rho from 0 to 3 (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | PSNR: 30.86 -> 27.39 | Hurt |
| move source KV injection start t_inj from 0.5 to 0.3 or 0.7 (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | FiVE-Acc: 51.17 / 51.94 / 52.10 | No clear effect |
| remove self-attention bridge (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | qualitative fidelity to source | Hurt |
| remove source-oriented guidance (ablation) | StreamEdit (Self Forcing) · FiVE-Bench | background alignment | Hurt |
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.
- VideoGrain — VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing (ICLR 2025) · better on 2 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
- AR-Edit: Training-Free Streaming Video Editing without Inversion (NeurIPS 2026 · similarity 0.90)
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text (CVPR 2025 · similarity 0.88)
- AdaState: Self-Evolving Anchors for Streaming Video Generation (NeurIPS 2026 · similarity 0.86)
- Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists (NeurIPS 2025 · similarity 0.86)
- ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way (CVPR 2025 · similarity 0.86)
- LongDiff: Training-Free Long Video Generation in One Go (CVPR 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.
