DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registration

TL;DR

DeepCLR introduces a novel end-to-end deep learning architecture for point cloud registration that predicts alignment without explicit correspondences, achieving state-of-the-art accuracy and efficiency on standard datasets.

Contribution

It proposes a correspondence-less, flow embedding-based neural network architecture for point cloud registration, eliminating the need for explicit point correspondences.

Findings

Achieves state-of-the-art accuracy on KITTI and ModelNet40 datasets.

Provides the lowest runtime among compared registration methods.

Effectively handles overlapping point clouds from different measurements.

Abstract

This work addresses the problem of point cloud registration using deep neural networks. We propose an approach to predict the alignment between two point clouds with overlapping data content, but displaced origins. Such point clouds originate, for example, from consecutive measurements of a LiDAR mounted on a moving platform. The main difficulty in deep registration of raw point clouds is the fusion of template and source point cloud. Our proposed architecture applies flow embedding to tackle this problem, which generates features that describe the motion of each template point. These features are then used to predict the alignment in an end-to-end fashion without extracting explicit point correspondences between both input clouds. We rely on the KITTI odometry and ModelNet40 datasets for evaluating our method on various point distributions. Our approach achieves state-of-the-art accuracy and the lowest run-time of the compared methods.