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 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%.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Mapped Convolutions
We present a versatile formulation of the convolution operation that we term a "mapped convolution." The standard convolution operation implicitly samples the pixel grid and computes a weighted sum. Our mapped convolutio…
Depth EstimationSpin-Weighted Spherical CNNs
Learning equivariant representations is a promising way to reduce sample and model complexity and improve the generalization performance of deep neural networks. The spherical CNNs are successful examples, producing SO(3…
Semantic SegmentationMöbius Convolutions for Spherical CNNs
M\"obius transformations play an important role in both geometry and spherical image processing - they are the group of conformal automorphisms of 2D surfaces and the spherical equivalent of homographies. Here we present…
DescriptiveImage SegmentationSemantic SegmentationScaling Spherical CNNs
Spherical CNNs generalize CNNs to functions on the sphere, by using spherical convolutions as the main linear operation. The most accurate and efficient way to compute spherical convolutions is in the spectral domain (vi…
Weather ForecastingSpherical convolutions and their application in molecular modelling
Convolutional neural networks are increasingly used outside the domain of image analysis, in particular in various areas of the natural sciences concerned with spatial data. Such networks often work out-of-the box, and i…
Feature Engineering