Superpixel Hierarchy

TL;DR

This paper introduces Super Hierarchy, a fast and accurate method for generating multi-scale superpixel segmentations in real-time, outperforming existing techniques in accuracy and speed.

Contribution

The paper presents a novel superpixel hierarchy algorithm that is both highly accurate and significantly faster than current state-of-the-art methods, enabling real-time multi-scale segmentation.

Findings

Super Hierarchy achieves state-of-the-art accuracy.

It is 10-100 times faster than comparable methods.

The method outperforms existing techniques in various applications.

Abstract

Superpixel segmentation is becoming ubiquitous in computer vision. In practice, an object can either be represented by a number of segments in finer levels of detail or included in a surrounding region at coarser levels of detail, and thus a superpixel segmentation hierarchy is useful for applications that require different levels of image segmentation detail depending on the particular image objects segmented. Unfortunately, there is no method that can generate all scales of superpixels accurately in real-time. As a result, a simple yet effective algorithm named Super Hierarchy (SH) is proposed in this paper. It is as accurate as the state-of-the-art but 1-2 orders of magnitude faster. The proposed method can be directly integrated with recent efficient edge detectors like the structured forest edges to significantly outperforms the state-of-the-art in terms of segmentation accuracy. Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.