Dynamic Spectral Residual Superpixels

TL;DR

This paper introduces a new superpixel segmentation method that combines spectral residual analysis with SLIC, improving boundary adherence and detail preservation while maintaining computational efficiency.

Contribution

It proposes a novel initialization and search metric based on spectral residuals, enhancing superpixel segmentation quality over existing methods.

Findings

Outperforms state-of-the-art superpixel algorithms in boundary accuracy.

Preserves fine image details better than traditional methods.

Maintains computational efficiency comparable to existing approaches.

Abstract

We consider the problem of segmenting an image into superpixels in the context of $k$-means clustering, in which we wish to decompose an image into local, homogeneous regions corresponding to the underlying objects. Our novel approach builds upon the widely used Simple Linear Iterative Clustering (SLIC), and incorporate a measure of objects' structure based on the spectral residual of an image. Based on this combination, we propose a modified initialisation scheme and search metric, which helps keeps fine-details. This combination leads to better adherence to object boundaries, while preventing unnecessary segmentation of large, uniform areas, while remaining computationally tractable in comparison to other methods. We demonstrate through numerical and visual experiments that our approach outperforms the state-of-the-art techniques.