Superpixel-Based Image Segmentation Using Squared 2-Wasserstein Distances

• URL: http://arxiv.org/abs/2601.17071v1
• Date: Thu, 22 Jan 2026 22:24:15 GMT
• Title: Superpixel-Based Image Segmentation Using Squared 2-Wasserstein Distances
• Authors: Jisui Huang, Andreas Alpers, Ke Chen, Na Lei,
• Abstract summary: We present an efficient method for image segmentation in the presence of strong inhomogeneities.<n>Superpixels are first grouped into superpixels via a linear least-squares assignment problem.<n>These superpixels are then greedily merged into object-level segments using the squared 2-Wasserstein distance between their empirical distributions.
• Score: 11.580076885777151
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Joint Superpixel and Self-Representation Learning for Scalable Hyperspectral Image Clustering [42.598744707088535]
  Subspace clustering is a powerful unsupervised approach for hyperspectral image (HSI) analysis.<n>Superpixel segmentation can improve efficiency by reducing the number of data points to process.<n>We propose a unified end-to-end framework that jointly optimize superpixel segmentation and subspace clustering.
  arXiv  Detail & Related papers  (2025-09-28T18:42:48Z)
• Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering [73.01141916544103]
  Hyperspectral image (HSI) clustering groups pixels into clusters without labeled data.<n>Most methods rely on superpixel segmentation and perform superpixel-level clustering based on graph neural networks (GNNs)<n>We propose a structural-spectral graph convolutional operator (SSGCO) tailored for graph-structured HSI superpixels to improve representation quality.
  arXiv  Detail & Related papers  (2025-06-11T16:41:34Z)
• Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images [73.01141916544103]
  Hyperspectral images (HSI) clustering is an important but challenging task.<n>We first use 3-D and 2-D hybrid convolutional neural networks to extract the high-order spatial and spectral features of HSI.<n>We then design a superpixel graph contrastive clustering model to learn discriminative superpixel representations.
  arXiv  Detail & Related papers  (2024-03-04T07:40:55Z)
• Superpixel-guided Discriminative Low-rank Representation of Hyperspectral Images for Classification [49.32130776974202]
  SP-DLRR is composed of two modules, i.e., the classification-guided superpixel segmentation and the discriminative low-rank representation. Experimental results on three benchmark datasets demonstrate the significant superiority of SP-DLRR over state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-25T10:47:26Z)
• AINet: Association Implantation for Superpixel Segmentation [82.21559299694555]
  We propose a novel textbfAssociation textbfImplantation (AI) module to enable the network to explicitly capture the relations between the pixel and its surrounding grids. Our method could not only achieve state-of-the-art performance but maintain satisfactory inference efficiency.
  arXiv  Detail & Related papers  (2021-01-26T10:40:13Z)
• Superpixel Segmentation Based on Spatially Constrained Subspace Clustering [57.76302397774641]
  We consider each representative region with independent semantic information as a subspace, and formulate superpixel segmentation as a subspace clustering problem. We show that a simple integration of superpixel segmentation with the conventional subspace clustering does not effectively work due to the spatial correlation of the pixels. We propose a novel convex locality-constrained subspace clustering model that is able to constrain the spatial adjacent pixels with similar attributes to be clustered into a superpixel.
  arXiv  Detail & Related papers  (2020-12-11T06:18:36Z)
• Superpixel Based Graph Laplacian Regularization for Sparse Hyperspectral Unmixing [1.14219428942199]
  We use a superpixel segmentation algorithm to extract the homogeneous regions by considering the image boundaries. We first extract the homogeneous regions, which are called superpixels, then a weighted graph in each superpixel is constructed by selecting $K$-nearest pixels in each superpixel. The spatial similarity is investigated using graph Laplacian regularization.
  arXiv  Detail & Related papers  (2020-07-28T07:30:50Z)
• ITSELF: Iterative Saliency Estimation fLexible Framework [68.8204255655161]
  Saliency object detection estimates the objects that most stand out in an image. We propose a superpixel-based ITerative Saliency Estimation fLexible Framework (ITSELF) that allows any user-defined assumptions to be added to the model. We compare ITSELF to two state-of-the-art saliency estimators on five metrics and six datasets.
  arXiv  Detail & Related papers  (2020-06-30T16:51:31Z)
• Robust superpixels using color and contour features along linear path [5.746869663956391]
  We propose a framework that provides accurate and regular Superpixels with Contour Adherence using Linear Path (SCALP)<n>A contour prior is also used to prevent the crossing of image boundaries when associating a pixel to a superpixel.<n>SCALP is extensively evaluated on standard segmentation dataset, and the obtained results outperform the ones of the state-of-the-art methods.
  arXiv  Detail & Related papers  (2019-03-17T23:00:13Z)
• SCALP: Superpixels with Contour Adherence using Linear Path [5.746869663956391]
  We propose a fast method to compute Superpixels with Contour Adherence using Linear Path (SCALP) in an iterative clustering framework.<n>The proposed framework produces compact and superpixels that adhere to contour contours.
  arXiv  Detail & Related papers  (2019-03-17T19:23:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.