Abstract | ||
---|---|---|
Convolutional Neural Networks (CNNs) have become the method of choice for learning problems involving 2D planar images. However, a number of problems of recent interest have created a demand for models that can analyze spherical images. Examples include omnidirectional vision for drones, robots, and autonomous cars, molecular regression problems, and global weather and climate modelling. A naive application of convolutional networks to a planar projection of the spherical signal is destined to fail, because the space-varying distortions introduced by such a projection will make translational weight sharing ineffective. In this paper we introduce the building blocks for constructing spherical CNNs. We propose a definition for the spherical cross-correlation that is both expressive and rotation-equivariant. The spherical correlation satisfies a generalized Fourier theorem, which allows us to compute it efficiently using a generalized (non-commutative) Fast Fourier Transform (FFT) algorithm. We demonstrate the computational efficiency, numerical accuracy, and effectiveness of spherical CNNs applied to 3D model recognition and atomization energy regression. |
Year | Venue | DocType |
---|---|---|
2018 | ICLR | Conference |
Volume | ISSN | Citations |
abs/1801.10130 | Proceedings of the International Conference on Learning
Representations, 2018 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taco Cohen | 1 | 228 | 17.82 |
Mario Geiger | 2 | 42 | 5.47 |
Jonas Köhler | 3 | 3 | 2.07 |
Max Welling | 4 | 4875 | 550.34 |