Learning Spherical Convolution for Fast Features from 360° Imagery

191 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Kernel Transformer Networks for Compact Spherical Convolution (2018, methodology): “The ﬁrst adapts the network architecture for equirectangu-lar projection and trains kernels of variable size to account for its distortions [37].”
DeepSphere: a graph-based spherical CNN (2020, methodology): “Exploiting the locally Euclidean property of the sphere, early attempts used standard 2D convolutions on a grid sampling of the sphere (Boomsma & Frellsen, 2017; Su & Grauman, 2017; Coors et al., 2018).”
Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery (2020, background): “In [29], Su et al. propose the use of convolution kernels of different sizes at different locations under equirectangular projections to compensate for this distortion.”