Unsupervised Point Cloud Registration with Self-Distillation

Understand

Rigid point cloud registration is a fundamental problem and highly relevant in robotics and autonomous driving.

• Nowadays deep learning methods can be trained to match a pair of point clouds, given the transformation between them.
• However, this training is often not scalable due to the high cost of collecting ground truth poses.
• Therefore, we present a self-distillation approach to learn point cloud registration in an unsupervised fashion.