PCRNet: Point Cloud Registration Network using PointNet Encoding

TL;DR

This paper introduces PCRNet, a novel point cloud registration network that leverages PointNet features to accurately align 3D point clouds, demonstrating robustness to noise and initial misalignments through extensive experiments.

Contribution

The paper proposes a new framework using PointNet features for point cloud registration, capable of handling shape-specific and general cases with improved robustness.

Findings

Effective alignment of point clouds demonstrated in simulations and real-world tests

Outperforms existing state-of-the-art registration methods

Robust to noise and initial misalignment

Abstract

PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion. However, recent works in literature have shown the sensitivity of the PointNet representation to pose misalignment. This paper presents a novel framework that uses the PointNet representation to align point clouds and perform registration for applications such as tracking, 3D reconstruction and pose estimation. We develop a framework that compares PointNet features of template and source point clouds to find the transformation that aligns them accurately. Depending on the prior information about the shape of the object formed by the point clouds, our framework can produce approaches that are shape specific or general to unseen shapes. The shape specific approach uses a Siamese architecture with fully connected (FC) layers and is robust to noise and initial misalignment in data. We perform extensive simulation and real-world experiments to validate the efficacy of our approach and compare the performance with state-of-art approaches.