Convolutions on Spherical Images
Abstract
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%.
Cite
Text
Eder and Frahm. "Convolutions on Spherical Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.Markdown
[Eder and Frahm. "Convolutions on Spherical Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/eder2019cvprw-convolutions/)BibTeX
@inproceedings{eder2019cvprw-convolutions,
title = {{Convolutions on Spherical Images}},
author = {Eder, Marc and Frahm, Jan-Michael},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {1-5},
url = {https://mlanthology.org/cvprw/2019/eder2019cvprw-convolutions/}
}