Official implementation of MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance
Hallee E. Wong, Jose Javier Gonzalez Ortiz, John Guttag, Adrian V. Dalca
- (2025-01-26) inference code and weights released
- (2024-12-19) preprint released!
We provide pre-trained weights here.
You can install multiverseg in two ways:
- With pip:
pip install git+https://github.com/halleewong/MultiverSeg.git
- Manually: cloning it and installing dependencies
git clone https://github.com/halleewong/MultiverSeg
python -m pip install -r ./MultiverSeg/requirements.txt
export PYTHONPATH="$PYTHONPATH:$(realpath ./MultiverSeg)"
First download the model checkpoints
cd checkpoints
./download.sh
Then see ./notebooks/inference.ipynb for a tutorial.
This project builds extensively on code originally developed for ScribblePrompt and UniverSeg
If you find our work or any of our materials useful, please cite our paper:
@article{wong2024multiverseg,
title={MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance},
author={Hallee E. Wong and Jose Javier Gonzalez Ortiz and John Guttag and Adrian V. Dalca},
journal={arXiv preprint arXiv:2412.15058},
year={2024},
}