Point Cloud Processing via Recurrent Set Encoding

TL;DR

This paper introduces a permutation-invariant neural network for 3D point cloud processing that combines a recurrent set encoder with a convolutional aggregator, achieving competitive accuracy with improved efficiency.

Contribution

The paper proposes a novel recurrent set encoding architecture that effectively captures spatial features in point clouds while being more computationally efficient than existing methods.

Findings

Competitive performance on benchmark datasets.

Significantly improved computational efficiency.

Effective spatial feature learning from unordered point sets.

Abstract

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.