Generalized Shortest Path-based Superpixels for 3D Spherical Image Segmentation

2025-09-24

AI Summary

Existing superpixel segmentation methods for 360° spherical images neglect spherical geometry, resulting in suboptimal accuracy and irregular superpixel shapes. To address this, we propose SphSPS—the first spherical superpixel segmentation method grounded in spherical shortest paths. Our approach generalizes graph-theoretic shortest-path concepts to the spherical manifold, enabling a geometrically consistent spherical distance metric and geometry-aware features. We further introduce a global spherical regularity metric that overcomes the failure of conventional compactness measures on curved surfaces. Integrating spherical centroid clustering with iterative optimization, SphSPS achieves high-fidelity segmentation. Evaluated on standard 360° datasets and synthetic omnidirectional road imagery, SphSPS consistently outperforms state-of-the-art planar and spherical methods, delivering significant improvements in segmentation accuracy, robustness to noise, and superpixel shape regularity.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

The growing use of wide angle image capture devices and the need for fast and accurate image analysis in computer visions have enforced the need for dedicated under-representation approaches. Most recent decomposition methods segment an image into a small number of irregular homogeneous regions, called superpixels. Nevertheless, these approaches are generally designed to segment standard 2D planar images, i.e., captured with a 90o angle view without distortion. In this work, we introduce a new general superpixel method called SphSPS (for Spherical Shortest Path-based Superpixels)1 , dedicated to wide 360o spherical or omnidirectional images. Our method respects the geometry of the 3D spherical acquisition space and generalizes the notion of shortest path between a pixel and a superpixel center, to fastly extract relevant clustering features. We demonstrate that considering the geometry of the acquisition space to compute the shortest path enables to jointly improve the segmentation accuracy and the shape regularity of superpixels. To evaluate this regularity aspect, we also generalize a global regularity metric to the spherical space, addressing the limitations of the only existing spherical compactness measure. Finally, the proposed SphSPS method is validated on the reference 360o spherical panorama segmentation dataset and on synthetic road omnidirectional images. Our method significantly outperforms both planar and spherical state-of-the-art approaches in terms of segmentation accuracy,robustness to noise and regularity, providing a very interesting tool for superpixel-based applications on 360o images.

Problem

• Segmenting wide 360° spherical images using superpixels
• Generalizing shortest path computation for 3D spherical geometry
• Improving segmentation accuracy and superpixel shape regularity

Innovation

• Generalizes shortest path for spherical superpixels
• Respects 3D spherical geometry for segmentation
• Introduces global regularity metric for spherical space