An Iterative Spanning Forest Framework for Superpixel Segmentation

TL;DR

This paper introduces an Iterative Spanning Forest framework for superpixel segmentation, allowing flexible component choices to improve segmentation quality and efficiency in 2D and 3D images.

Contribution

It proposes a novel flexible framework for superpixel segmentation based on Image Foresting Transforms, with multiple methods and comprehensive comparisons.

Findings

Some ISF methods outperform state-of-the-art baselines.

The framework is effective for 2D and 3D datasets.

ISF achieves competitive efficiency and effectiveness.

Abstract

Superpixel segmentation has become an important research problem in image processing. In this paper, we propose an Iterative Spanning Forest (ISF) framework, based on sequences of Image Foresting Transforms, where one can choose i) a seed sampling strategy, ii) a connectivity function, iii) an adjacency relation, and iv) a seed pixel recomputation procedure to generate improved sets of connected superpixels (supervoxels in 3D) per iteration. The superpixels in ISF structurally correspond to spanning trees rooted at those seeds. We present five ISF methods to illustrate different choices of its components. These methods are compared with approaches from the state-of-the-art in effectiveness and efficiency. The experiments involve 2D and 3D datasets with distinct characteristics, and a high level application, named sky image segmentation. The theoretical properties of ISF are demonstrated in the supplementary material and the results show that some of its methods are competitive with or superior to the best baselines in effectiveness and efficiency.