Multiresolution Tree Networks for 3D Point Cloud Processing

ECCV, 2018.

Cited by: 47|Views28
EI
Weibo:
Our key idea is to represent a shape as a set of locality-preserving 1D ordered list of points at multiple resolutions, allowing efficient 1D convolution and pooling operations

Abstract:

We present multiresolution tree-structured networks to process point clouds for 3D shape understanding and generation tasks. Our network represents a 3D shape as a set of locality-preserving 1D ordered list of points at multiple resolutions. This allows efficient feed-forward processing through 1D convolutions, coarse-to-fine analysis thr...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments