Research map / Video / Video segmentation and tracking
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
Yang Fu, Yike Zheng, Ziyun Dai, Henghui Ding
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 Effect Consistency loss (ablation) | EffectErase (real data) · VOR-Eval | FVD: 368.664 -> 354.545 | Improved |
| add Effect Consistency loss (ablation) | EffectErase (real data) · VOR-Eval | PSNR: 20.409 -> 21.020 | Improved |
| add Effect Consistency loss (ablation) | EffectErase (real data) · VOR-Eval | LPIPS: 0.243 -> 0.224 | Improved |
| add Task-Aware Region Guidance (ablation) | EffectErase (real + EC) · VOR-Eval | SSIM: 0.737 -> 0.780 | Improved |
| add Task-Aware Region Guidance (ablation) | EffectErase (real + EC) · VOR-Eval | PSNR: 21.020 -> 23.101 | Improved |
| add Task-Aware Region Guidance (ablation) | EffectErase (real + EC) · VOR-Eval | FVD: 354.545 -> 349.094 | Improved |
| add synthesized training data (ablation) | EffectErase (real + EC + TARG) · VOR-Eval | LPIPS: 0.193 -> 0.170 | Improved |
| add synthesized training data (ablation) | EffectErase (real + EC + TARG) · VOR-Eval | PSNR: 23.101 -> 23.750 | Improved |
| add synthesized training data (ablation) | EffectErase (real + EC + TARG) · VOR-Eval | FVD: 349.094 -> 342.871 | Improved |
| use EffectErase instead of ROSE | video object removal · ROSE-Benchmark | PSNR: 31.122 -> 32.161 | Improved |
| use EffectErase instead of ROSE | video object removal · VOR-Eval | PSNR: 22.966 -> 23.750 | Improved |
| use EffectErase instead of ROSE | video object removal · VOR-Eval effect region | PSNR: 30.267 -> 32.747 | 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.
- ROSE — ROSE: Remove Objects with Side Effects in Videos (NeurIPS 2025) · better on 11 of 11 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
- Object-WIPER: Training-Free Object and Associated Effect Removal in Videos (CVPR 2026 · similarity 0.93)
- ROSE: Remove Objects with Side Effects in Videos (NeurIPS 2025 · similarity 0.89)
- MiniMax-Remover: Taming Bad Noise Helps Video Object Removal (NeurIPS 2025 · similarity 0.87)
- Generative Omnimatte: Learning to Decompose Video into Layers (CVPR 2025 · similarity 0.87)
- GeoRemover: Removing Objects and Their Causal Visual Artifacts (NeurIPS 2025 · similarity 0.86)
- SmartEraser: Remove Anything from Images using Masked-Region Guidance (CVPR 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.
