AI Paper Atlas

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

CVPR 2026 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Effect Consistency loss (ablation)EffectErase (real data) · VOR-EvalFVD: 368.664 -> 354.545Improved
add Effect Consistency loss (ablation)EffectErase (real data) · VOR-EvalPSNR: 20.409 -> 21.020Improved
add Effect Consistency loss (ablation)EffectErase (real data) · VOR-EvalLPIPS: 0.243 -> 0.224Improved
add Task-Aware Region Guidance (ablation)EffectErase (real + EC) · VOR-EvalSSIM: 0.737 -> 0.780Improved
add Task-Aware Region Guidance (ablation)EffectErase (real + EC) · VOR-EvalPSNR: 21.020 -> 23.101Improved
add Task-Aware Region Guidance (ablation)EffectErase (real + EC) · VOR-EvalFVD: 354.545 -> 349.094Improved
add synthesized training data (ablation)EffectErase (real + EC + TARG) · VOR-EvalLPIPS: 0.193 -> 0.170Improved
add synthesized training data (ablation)EffectErase (real + EC + TARG) · VOR-EvalPSNR: 23.101 -> 23.750Improved
add synthesized training data (ablation)EffectErase (real + EC + TARG) · VOR-EvalFVD: 349.094 -> 342.871Improved
use EffectErase instead of ROSEvideo object removal · ROSE-BenchmarkPSNR: 31.122 -> 32.161Improved
use EffectErase instead of ROSEvideo object removal · VOR-EvalPSNR: 22.966 -> 23.750Improved
use EffectErase instead of ROSEvideo object removal · VOR-Eval effect regionPSNR: 30.267 -> 32.747Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy