# Deep Spherical Superpixels

arXiv: https://arxiv.org/abs/2407.17354 · HTML: https://mlsanity.com/paper/2407.17354/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 24 Jul 2024.

## Builds on (most cited first, 13 of 13)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving](https://mlsanity.com/paper/1905.01489/) (2019)
- [HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation](https://mlsanity.com/paper/1901.03861/) (2019)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Capturing Omni-Range Context for Omnidirectional Segmentation](https://mlsanity.com/paper/2103.05687/) (2021)
- [Omnidirectional CNN for Visual Place Recognition and Navigation](https://mlsanity.com/paper/1803.04228/) (2018)
- [3D Scene Geometry Estimation from 360^circ Imagery: A Survey](https://mlsanity.com/paper/2401.09252/) (2024)
- [Superpixel Segmentation Using Gaussian Mixture Model](https://mlsanity.com/paper/1612.08792/) (2016)
- [Robust superpixels using color and contour features along linear path](https://mlsanity.com/paper/1903.07193/) (2019)
- [Evaluation Framework of Superpixel Methods with a Global Regularity Measure](https://mlsanity.com/paper/1903.07162/) (2019)

## Abstract (arXiv)

Over the years, the use of superpixel segmentation has become very popular in various applications, serving as a preprocessing step to reduce data size by adapting to the content of the image, regardless of its semantic content. While the superpixel segmentation of standard planar images, captured with a 90deg field of view, has been extensively studied, there has been limited focus on dedicated methods to omnidirectional or spherical images, captured with a 360deg field of view. In this study, we introduce the first deep learning-based superpixel segmentation approach tailored for omnidirectional images called DSS (for Deep Spherical Superpixels). Our methodology leverages on spherical CNN architectures and the differentiable K-means clustering paradigm for superpixels, to generate superpixels that follow the spherical geometry. Additionally, we propose to use data augmentation techniques specifically designed for 360deg images, enabling our model to efficiently learn from a limited set of annotated omnidirectional data. Our extensive validation across two datasets demonstrates that taking into account the inherent circular geometry of such images into our framework improves the segmentation performance over traditional and deep learning-based superpixel methods. Our code is available online.