Abstract | ||
---|---|---|
We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar to the regular grid CNN kernels, the spherical kernel maintains translation-invariance and asymmetry properties, where the former guarantees weight sharing among similar local struc... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TPAMI.2020.2983410 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Three-dimensional displays,Kernel,Convolution,Neural networks,Feature extraction,Semantics,Computer architecture | Journal | 43 |
Issue | ISSN | Citations |
10 | 0162-8828 | 12 |
PageRank | References | Authors |
0.67 | 15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huan Lei | 1 | 21 | 1.11 |
Faisal Shafait | 2 | 1324 | 88.97 |
A. Mian | 3 | 1679 | 84.89 |