• Computer Science
  • Published in ArXiv 2018

ZerNet: Convolutional Neural Networks on Arbitrary Surfaces via Zernike Local Tangent Space Estimation

@article{Sun2018ZerNetCN,
  title={ZerNet: Convolutional Neural Networks on Arbitrary Surfaces via Zernike Local Tangent Space Estimation},
  author={Zhiyu Sun and Jia Lu and Stephen Baek},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.01082}
}
In many fields of science and engineering, geometric features play a key role in understanding certain quantity or phenomena. Recently, convolutional neural networks (CNNs) have been shown to possess a promising capability of extracting and codifying features from visual information. However, the application of such capable CNNs has been quite limited to mostly computer vision problems where the visual information is inherently given on a grid-like structure. This, unfortunately, was not the… CONTINUE READING
1
Twitter Mention

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Geodesic Convolutional Neural Networks on Riemannian Manifolds

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Anisotropic Diffusion Descriptors

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL