papers AI Learner
The Github is limit! Click to go to the new site.

Convolutions on Spherical Images

2019-05-21
Marc Eder, Jan-Michael Frahm

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%.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.08409

PDF

http://arxiv.org/pdf/1905.08409


Similar Posts

Comments