Accurate Point Cloud Registration with Robust Optimal Transport

TL;DR

This paper demonstrates that robust optimal transport significantly improves point cloud registration accuracy and scalability across various challenging tasks, including partial shape matching, scene flow estimation, and complex lung vascular registration.

Contribution

It introduces the use of modern robust OT solvers to enhance both optimization-based and deep learning registration methods, providing state-of-the-art results and a new challenging dataset.

Findings

Achieved state-of-the-art accuracy on Kitti and lung registration tasks.

Demonstrated robustness and scalability of OT-based registration methods.

Released a new dataset of lung vascular trees for benchmarking.

Abstract

This work investigates the use of robust optimal transport (OT) for shape matching. Specifically, we show that recent OT solvers improve both optimization-based and deep learning methods for point cloud registration, boosting accuracy at an affordable computational cost. This manuscript starts with a practical overview of modern OT theory. We then provide solutions to the main difficulties in using this framework for shape matching. Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric registration of lung vascular trees between inspiration and expiration. Our OT-based methods achieve state-of-the-art results on Kitti and for the challenging lung registration task, both in terms of accuracy and scalability. We also release PVT1010, a new public dataset of 1,010 pairs of lung vascular trees with densely sampled points. This dataset provides a challenging use case for point cloud registration algorithms with highly complex shapes and deformations. Our work demonstrates that robust OT enables fast pre-alignment and fine-tuning for a wide range of registration models, thereby providing a new key method for the computer vision toolbox. Our code and dataset are available online at: https://github.com/uncbiag/robot.