# Superpixel-Based Image Segmentation Using Squared 2-Wasserstein Distances

arXiv: https://arxiv.org/abs/2601.17071 · HTML: https://mlsanity.com/paper/2601.17071/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 74 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Statistical Aspects of Wasserstein Distances](https://mlsanity.com/paper/1806.05500/) (2018)
- [Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications](https://mlsanity.com/paper/2304.05750/) (2023)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [Generalized balanced power diagrams for 3D representations of polycrystals](https://mlsanity.com/paper/1411.4535/) (2014)
- [Power-SLIC: Fast Superpixel Segmentations by Diagrams](https://mlsanity.com/paper/2012.11772/) (2020)
- [Dynamic grain models via fast heuristics for diagram representations](https://mlsanity.com/paper/2204.06430/) (2022)

## Abstract (arXiv)

We present an efficient method for image segmentation in the presence of strong inhomogeneities. The approach can be interpreted as a two-level clustering procedure: pixels are first grouped into superpixels via a linear least-squares assignment problem, which can be viewed as a special case of a discrete optimal transport (OT) problem, and these superpixels are subsequently greedily merged into object-level segments using the squared 2-Wasserstein distance between their empirical distributions. In contrast to conventional superpixel merging strategies based on mean-color distances, our framework employs a distributional OT distance, yielding a mathematically unified formulation across both clustering levels. Numerical experiments demonstrate that this perspective leads to improved segmentation accuracy on challenging images while retaining high computational efficiency.