<div align="center"> <header class="hero"> <div class="wrap"> <div class="top"> <h1 class="title">EffectErase: Joint Video Object Removal<br />and Insertion for High-Quality Effect Erasing</h1> <p class="venue">CVPR 2026</p> <p class="authors"> <a href="https://www.yangfu.site/" target="_blank" rel="noreferrer">Yang Fu</a>  ·  <a href="https://henghuiding.com/group/" target="_blank" rel="noreferrer">Yike Zheng</a>  ·  <a href="https://github.com/oliviadzy" target="_blank" rel="noreferrer">Ziyun Dai</a>  ·  <a href="https://henghuiding.com/" target="_blank" rel="noreferrer">Henghui Ding</a><span class="muted">†</span> </p> <p class="affiliations"> Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, China <br /> <span class="muted">† Corresponding author</span> </p> <div> <h4 align="center"> <a href="https://henghuiding.com/EffectErase/" target="_blank" rel="noreferrer"> <img src="https://img.shields.io/badge/🐳-Project%20Page-blue" alt="Project Page" /> </a> <a href="https://cvpr.thecvf.com/virtual/2026/papers.html" target="_blank" rel="noreferrer"> <img src="https://img.shields.io/badge/Paper-CVPR%202026-green" alt="Paper" /> </a> <a href="http://arxiv.org/abs/2603.19224" target="_blank" rel="noreferrer"> <img src="https://img.shields.io/badge/arXiv-EffectErase-red" alt="arXiv" /> </a> <a href="https://huggingface.co/datasets/FudanCVL/EffectErase" target="_blank" rel="noreferrer"> <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-Hugging%20Face-yellow" alt="Dataset" /> </a> </h4> </div> For more visual results, go checkout our <a href="https://henghuiding.com/EffectErase/" target="_blank" rel="noreferrer">project page</a>. </div> </div> </header>

</div>

Result

Quick Start

Setup repository and environment

git clone git@github.com:FudanCVL/EffectErase.git
cd EffectErase
pip install -e .

Download weights

hf download alibaba-pai/Wan2.1-Fun-1.3B-InP --local-dir Wan-AI/Wan2.1-Fun-1.3B-InP
hf download FudanCVL/EffectErase EffectErase.ckpt --local-dir ./

Run the script
```
bash script/test_remove.sh
```
You can edit script/test_remove.sh and change these three paths to use your own data:
- --fg_bg_path
- --mask_path
- --output_path
--mask_path is a mask video generated by SAM2.1 (sam2.1_hiera_b+), aligned with --fg_bg_path.

BibTeX

Please consider to cite:

@inproceedings{fu2026EffectErase,
  title={{EffectErase}: Joint Video Object Removal and Insertion for High-Quality Effect Erasing},
  author={Fu, Yang and Zheng, Yike and Dai, Ziyun and Ding, Henghui},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2026}
}

Contact

If you have any questions, please feel free to reach me out at aleeyanger@gmail.com.

Acknowledgement

This code is based on DiffSynth-Studio. Thanks for their awesome works！

License

This project is licensed under CC BY-NC 4.0.

For research purposes only. Commercial use is strictly prohibited.

EffectErase

Install / Use

README