---
license: cc-by-nc-sa-4.0
pipeline_tag: image-segmentation
---

# SAM2Matting: Generalized Image and Video Matting

This repository contains the official checkpoints for **SAM2Matting**, a generalized matting framework that decouples high-level tracking from dedicated low-level matting to support robust image and video matting of any open-world targets.

[📄 Paper](https://huggingface.co/papers/2606.27339) | [🏠 Project Page](https://henghuiding.com/SAM2Matting/) | [💻 GitHub](https://github.com/FudanCVL/SAM2Matting)

<p align="center">
  <img src="https://raw.githubusercontent.com/FudanCVL/SAM2Matting/main/assets/teaser.png" width="90%" alt="SAM2Matting qualitative results"/>
</p>

## Highlights
- **Decoupled design**: Combines a VOS tracker for temporal consistency with ROI Detection & Progressive Matting for fine details.
- **Image-only training, video SOTA**: Strong zero-shot video matting performance without requiring expensive video matting datasets.
- **Diverse prompts**: Supports masks, points, boxes, and text prompts.
- **Open-world generalization**: Robust matting for humans, animals, anime, translucent objects, and rapid-motion scenes.

## Installation

To run SAM2Matting locally, clone the repository and install the dependencies:

```bash
# clone the repo and enter directory
git clone https://github.com/FudanCVL/SAM2Matting.git
cd SAM2Matting

# create and activate conda environment
conda create -n sam2matting python=3.10 -y
conda activate sam2matting

# install required packages
pip install -r requirements.txt
```

## Quick Start

The codebase provides separate inference scripts for image and video matting. 

To run video matting on a sample with SAM2-based trackers, run:

```bash
python inference_video_sam2.py --save_mp4
```

To enable compilation for faster execution (though the first run may be slower):

```bash
python inference_video_sam2.py --save_mp4 --compiled
```

## Citation

If you find SAM2Matting useful in your research, please consider citing the work:

```bibtex
@inproceedings{SAM2Matting,
  title={{SAM2Matting}: Generalized Image and Video Matting},
  author={Shen, Ruiqi and Jie, Guangquan and Liu, Chang and Ding, Henghui},
  booktitle={European Conference on Computer Vision (ECCV)},
  year={2026}
}
```