SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registration

TL;DR

SphereNet introduces a noise-robust, general descriptor for point cloud registration using spherical voxelization, interpolation, and a spherical CNN, significantly improving accuracy under high noise and unseen data.

Contribution

The paper proposes SphereNet, a novel spherical CNN-based descriptor that enhances robustness to noise and generalizes well to unseen datasets in point cloud registration.

Findings

Increases feature matching recall by over 25% under high noise.

Achieves state-of-the-art registration recall on 3DMatch and 3DLoMatch.

Demonstrates superior generalization on unseen datasets.

Abstract

Point cloud registration is to estimate a transformation to align point clouds collected in different perspectives. In learning-based point cloud registration, a robust descriptor is vital for high-accuracy registration. However, most methods are susceptible to noise and have poor generalization ability on unseen datasets. Motivated by this, we introduce SphereNet to learn a noise-robust and unseen-general descriptor for point cloud registration. In our method, first, the spheroid generator builds a geometric domain based on spherical voxelization to encode initial features. Then, the spherical interpolation of the sphere is introduced to realize robustness against noise. Finally, a new spherical convolutional neural network with spherical integrity padding completes the extraction of descriptors, which reduces the loss of features and fully captures the geometric features. To evaluate our methods, a new benchmark 3DMatch-noise with strong noise is introduced. Extensive experiments are carried out on both indoor and outdoor datasets. Under high-intensity noise, SphereNet increases the feature matching recall by more than 25 percentage points on 3DMatch-noise. In addition, it sets a new state-of-the-art performance for the 3DMatch and 3DLoMatch benchmarks with 93.5\% and 75.6\% registration recall and also has the best generalization ability on unseen datasets.