Point Cloud Processing via Recurrent Set Encoding

11/25/2019
by   Pengxiang Wu, et al.
34

We present a new permutation-invariant network for 3D point cloud processing. Our network is composed of a recurrent set encoder and a convolutional feature aggregator. Given an unordered point set, the encoder firstly partitions its ambient space into parallel beams. Points within each beam are then modeled as a sequence and encoded into subregional geometric features by a shared recurrent neural network (RNN). The spatial layout of the beams is regular, and this allows the beam features to be further fed into an efficient 2D convolutional neural network (CNN) for hierarchical feature aggregation. Our network is effective at spatial feature learning, and competes favorably with the state-of-the-arts (SOTAs) on a number of benchmarks. Meanwhile, it is significantly more efficient compared to the SOTAs.

READ FULL TEXT

page 6

page 7

research
04/22/2019

Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features

Learning on point cloud is eagerly in demand because the point cloud is ...
research
04/16/2019

Relation-Shape Convolutional Neural Network for Point Cloud Analysis

Point cloud analysis is very challenging, as the shape implied in irregu...
research
10/18/2019

PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing

Point cloud is attracting more and more attention in the community. Howe...
research
04/11/2019

Adaptive Hierarchical Down-Sampling for Point Cloud Classification

While several convolution-like operators have recently been proposed for...
research
09/30/2022

Explaining Hierarchical Features in Dynamic Point Cloud Processing

This paper aims at bringing some light and understanding to the field of...
research
06/02/2022

Lossless Compression of Point Cloud Sequences Using Sequence Optimized CNN Models

We propose a new paradigm for encoding the geometry of point cloud seque...
research
09/09/2019

DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing

Point cloud processing is very challenging, as the diverse shapes formed...

Please sign up or login with your details

Forgot password? Click here to reset