Surface Networks Via General Covers
2018 · Niv Haim, Nimrod Segol, Heli Ben-Hamu, et al.
Abstract
Developing deep learning techniques for geometric data is an active and fruitful research area. This paper tackles the problem of sphere-type surface learning by developing a novel surface-to-image representation. Using this representation we are able to quickly adapt successful CNN models to the surface setting. The surface-image representation is based on a covering map from the image domain to the surface. Namely, the map wraps around the surface several times, making sure that every part of the surface is well represented in the image. Differently from previous surface-to-image representations, we provide a low distortion coverage of all surface parts in a single image. Specifically, for the use case of learning spherical signals, our representation provides a low distortion alternative to several popular spherical parameterizations used in deep learning. We have used the surface-to-image representation to apply standard CNN architectures to 3D models as well as spherical signa
Authors
(none)
Tags
Stats
Related papers
- Rotation-invariant Autoencoders For Signals On Spheres (2020)0.00
- Spnet: Deep 3D Object Classification And Retrieval Using Stereographic Projection (2018)10.74
- Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
- Learning Geodesic-aware Local Features From RGB-D Images (2022)6.34
- Representing Deep Neural Networks Latent Space Geometries With Graphs (2020)7.50
- Connecting Neural Models Latent Geometries With Relative Geodesic Representations (2025)0.00
- A Convolutional Architecture For 3D Model Embedding (2021)0.00
- Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences (2018)11.39