# Convolutions on Spherical Images

arXiv: https://arxiv.org/abs/1905.08409 · HTML: https://mlsanity.com/paper/1905.08409/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2019.

## Built on by (most cited first, 12 of 12)

- [Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Cameras](https://mlsanity.com/paper/2103.17001/) (2021)
- [Equivariance versus Augmentation for Spherical Images](https://mlsanity.com/paper/2202.03990/) (2022)
- [HEAL-SWIN: A Vision Transformer On The Sphere](https://mlsanity.com/paper/2307.07313/) (2023)
- [3D Scene Geometry Estimation from 360^circ Imagery: A Survey](https://mlsanity.com/paper/2401.09252/) (2024)
- [PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation](https://mlsanity.com/paper/2202.01323/) (2022)
- [Geometry Fidelity for Spherical Images](https://mlsanity.com/paper/2407.18207/) (2024)
- [ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers](https://mlsanity.com/paper/2303.06907/) (2023)
- [VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation](https://mlsanity.com/paper/2603.18943/) (2026)
- [Rigidity Preserving Image Transformations and Equivariance in Perspective](https://mlsanity.com/paper/2201.13065/) (2022)
- [Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA) for Remote Land-use Change Detection](https://mlsanity.com/paper/2303.14322/) (2023)
- [Quality Assessment of Super-Resolved Omnidirectional Image Quality Using Tangential Views](https://mlsanity.com/paper/2101.10396/) (2021)
- [Spherical Convolution empowered FoV Prediction in 360-degree Video Multicast with Limited FoV Feedback](https://mlsanity.com/paper/2201.12525/) (2022)

## Abstract (arXiv)

Applying convolutional neural networks to spherical images requires particular considerations. We look to the millennia of work on cartographic map projections to provide the tools to define an optimal representation of spherical images for the convolution operation. We propose a representation for deep spherical image inference based on the icosahedral Snyder equal-area (ISEA) projection, a projection onto a geodesic grid, and show that it vastly exceeds the state-of-the-art for convolution on spherical images, improving semantic segmentation results by 12.6%.