Convolutions on Spherical Images
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...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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%. |
---|---|
DOI: | 10.48550/arxiv.1905.08409 |