Spatial Transformer for 3D Points

CoRR, 2019.

Cited by: 0|Bibtex|Views18|Links
EI

Abstract:

Point cloud is an efficient representation of 3D visual data, and enables deep neural networks to effectively understand and model the 3D visual world. All the previous methods used the same original point cloud location at different layers of the network to define "local patches". Depending on the neighborhood of the local patches, the...More

Code:

Data:

Your rating :
0

 

Tags
Comments