用分布距离合并超像素，提升复杂图像分割精度。
Superpixel-Based Image Segmentation Using Squared 2-Wasserstein Distances
- 先分超像素，再用平方2-Wasserstein距离合并
- 在挑战性图像上分割准确率更高
- 数学统一框架，适合图像分割研究者
我们提出一种高效图像分割方法，适用于强不均匀场景。该方法可视为两级聚类：首先通过线性最小二乘分配问题将像素分组为超像素，这可看作离散最优传输（OT）问题的特例；随后利用超像素经验分布间的平方2-Wasserstein距离，贪心地将其合并为物体级区域。与传统基于均色距的超像素合并策略不同，本框架采用分布型OT距离，使两级聚类具有数学统一性。数值实验表明，该方法在挑战性图像上显著提升分割精度，同时保持高计算效率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。