# MultiStar: Instance Segmentation of Overlapping Objects with Star-Convex Polygons

arXiv: https://arxiv.org/abs/2011.13228 · HTML: https://mlsanity.com/paper/2011.13228/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [CPP-Net: Context-aware Polygon Proposal Network for Nucleus Segmentation](https://mlsanity.com/paper/2102.06867/) (2021)
- [Deep Learning for Computational Cytology: A Survey](https://mlsanity.com/paper/2202.05126/) (2022)
- [DoNet: Deep De-overlapping Network for Cytology Instance Segmentation](https://mlsanity.com/paper/2303.14373/) (2023)
- [Bubble identification from images with machine learning methods](https://mlsanity.com/paper/2202.03107/) (2022)
- [Defining the boundaries: challenges and advances in identifying cells in microscopy images](https://mlsanity.com/paper/2311.08269/) (2023)
- [Overlap-aware segmentation for topological reconstruction of obscured objects](https://mlsanity.com/paper/2510.06194/) (2025)

## Abstract (arXiv)

Instance segmentation of overlapping objects in biomedical images remains a largely unsolved problem. We take up this challenge and present MultiStar, an extension to the popular instance segmentation method StarDist. The key novelty of our method is that we identify pixels at which objects overlap and use this information to improve proposal sampling and to avoid suppressing proposals of truly overlapping objects. This allows us to apply the ideas of StarDist to images with overlapping objects, while incurring only a small overhead compared to the established method. MultiStar shows promising results on two datasets and has the advantage of using a simple and easy to train network architecture.