Fast and accurate superpixel algorithms for 360° images

Superpixels are fundamental in many visual computing applications, and most existing algorithms are designed to work with pinhole-based images. However, immersive applications are gaining visibility with the growing number of devices for capturing and visualizing 360 degrees media. This paper introduces two fast and accurate superpixel algorithms tailored to the spherical domain. The methods are assessed under common figures of merit, and a benchmark annotated dataset. Additionally, an annotation-free evaluation metric for exploiting larger datasets is introduced. The methods introduced in this paper perform quantitatively close to or better than state-of-the-art approaches and are faster. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

Superpixels are fundamental in visual computing applications, with existing algorithms designed for pinhole-based images. This paper introduces two fast and accurate superpixel algorithms tailored to the spherical domain, outperforming existing approaches in terms of performance and speed.