Research map / Video / Video generation
PRIMEdit: Probability Redistribution for Instance-Aware Multi-Object Video Editing With a New Benchmark Dataset
Samuel Teodoro, Agus Gunawan, Soo Ye Kim, Jihyong Oh, Munchurl Kim
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 IPR (cross-attention probability redistribution) to DMS-only (ablation) | PRIMEdit · MIVE | IA: 0.4920 -> 0.5369 | Improved |
| add IPR to DMS-only (ablation) | PRIMEdit · MIVE | CIA: 0.6497 -> 0.6705 | Hurt |
| add IPR to DMS-only (ablation) | PRIMEdit · MIVE | LTC: 0.9564 -> 0.9552 | Hurt |
| add PNS after SNS (full DMS vs SNS only) (ablation) | PRIMEdit · MIVE | LTC: 0.9503 -> 0.9552 | Improved |
| add PNS after SNS (full DMS vs SNS only) (ablation) | PRIMEdit · MIVE | CIA: 0.6743 -> 0.6705 | Hurt |
| add SNS before PNS (full DMS vs PNS only) (ablation) | PRIMEdit · MIVE | CIA: 0.6718 -> 0.6705 | Hurt |
| add SNS before PNS (full DMS vs PNS only) (ablation) | PRIMEdit · MIVE | LTC: 0.9542 -> 0.9552 | Improved |
| add re-inversion after latent fusion (ablation) | PRIMEdit · MIVE | IA: 0.5323 -> 0.5369 | Improved |
| add re-inversion after latent fusion (ablation) | PRIMEdit · MIVE | LTC: 0.9535 -> 0.9552 | Improved |
| add re-inversion after latent fusion (ablation) | PRIMEdit · MIVE | CIA: 0.6728 -> 0.6705 | Hurt |
| replace DenseDiffusion modulation with IPR (ablation) | PRIMEdit · MIVE | LPIPS: 0.0604 -> 0.0586 | Improved |
| replace DenseDiffusion modulation with IPR (ablation) | PRIMEdit · MIVE | IA: 0.5845 -> 0.5369 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- VideoGrain — VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing (ICLR 2025) · better on 7 of 8 shared results
- ControlVideo — ControlVideo: Training-free Controllable Text-to-video Generation (ICLR 2024) · 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
- ImgEdit: A Unified Image Editing Dataset and Benchmark (NeurIPS 2025 · similarity 0.86)
- VEU-Bench: Towards Comprehensive Understanding of Video Editing (CVPR 2025 · similarity 0.85)
- Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists (NeurIPS 2025 · similarity 0.85)
- EditBoard: Towards a Comprehensive Evaluation Benchmark for Text-Based Video Editing Models (AAAI 2025 · similarity 0.85)
- Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models (ICLR 2024 · similarity 0.85)
- VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling (NeurIPS 2026 · 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.
