TL;DR
This paper introduces robust loss functions based on Best Buddies Similarity for point cloud registration, demonstrating improved accuracy and robustness in various challenging scenarios including sparse and noisy data.
Contribution
The paper proposes novel loss functions inspired by BBS for point cloud registration and develops algorithms that outperform existing methods in robustness and accuracy.
Findings
BBR algorithms are robust to noise, outliers, and distractors.
BBR-F achieves state-of-the-art accuracy on automotive lidar datasets.
The methods work well with extremely sparse point clouds.
Abstract
We propose new, and robust, loss functions for the point cloud registration problem. Our loss functions are inspired by the Best Buddies Similarity (BBS) measure that counts the number of mutual nearest neighbors between two point sets. This measure has been shown to be robust to outliers and missing data in the case of template matching for images. We present several algorithms, collectively named Best Buddy Registration (BBR), where each algorithm consists of optimizing one of these loss functions with Adam gradient descent. The loss functions differ in several ways, including the distance function used (point-to-point vs. point-to-plane), and how the BBS measure is combined with the actual distances between pairs of points. Experiments on various data sets, both synthetic and real, demonstrate the effectiveness of the BBR algorithms, showing that they are quite robust to noise,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsAdam
