metadata
license: cc-by-nc-sa-4.0
pipeline_tag: image-segmentation
SAM-MT: Real-Time Interactive Multi-Target Video Segmentation
This repository contains the official checkpoint for SAM-MT, presented in the paper SAM-MT: Real-Time Interactive Multi-Target Video Segmentation.
- Project Page: henghuiding.com/SAM-MT
- Repository: GitHub - FudanCVL/SAM-MT
SAM-MT is an efficient interactive multi-target video segmentation framework that maintains near-single-object efficiency (FPS and VRAM) as target count increases, while maintaining robust video segmentation performance.
Highlights
- Real-time speed: 36+ FPS with 10 targets on a single NVIDIA RTX A6000 GPU.
- Individual-global representation: Models individual targets and global scene within a unified framework.
- Interactive multi-target video segmentation: Simple clicks for target specification.
Quick Start
Installation
# clone the repo and enter directory
git clone https://github.com/FudanCVL/SAM-MT.git
cd SAM-MT
# create and activate conda environment
conda create -n sammt python=3.10 -y
conda activate sammt
# install required packages
pip install -r requirements.txt
Inference
By default, place the downloaded checkpoint under the checkpoints/ directory.
# Basic inference (coordinates required)
python inference.py
# Interactive Gradio demo
python inference_gradio.py
Citation
If you find SAM-MT useful in your research, please consider citing:
@inproceedings{SAM-MT,
title={{SAM-MT}: Real-Time Interactive Multi-Target Video Segmentation},
author={Shen, Ruiqi and Liu, Chang and Ding, Henghui},
booktitle={European Conference on Computer Vision (ECCV)},
year={2026}
}