UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration

TL;DR

This paper introduces UMERegRobust, a robust point cloud registration method that extends the Universal Manifold Embedding framework with new features and loss functions, achieving state-of-the-art results especially in large rotation scenarios.

Contribution

The paper presents a novel UME-compatible feature extraction method with a contrastive loss and sampling equalizer, enhancing robustness in point cloud registration.

Findings

Outperforms state-of-the-art on KITTI with +9% accuracy at strict thresholds

Achieves +45% improvement on RotKITTI benchmark

Effective in scenarios with large rotations and partial overlaps

Abstract

In this paper, we adopt the Universal Manifold Embedding (UME) framework for the estimation of rigid transformations and extend it, so that it can accommodate scenarios involving partial overlap and differently sampled point clouds. UME is a methodology designed for mapping observations of the same object, related by rigid transformations, into a single low-dimensional linear subspace. This process yields a transformation-invariant representation of the observations, with its matrix form representation being covariant (i.e. equivariant) with the transformation. We extend the UME framework by introducing a UME-compatible feature extraction method augmented with a unique UME contrastive loss and a sampling equalizer. These components are integrated into a comprehensive and robust registration pipeline, named UMERegRobust. We propose the RotKITTI registration benchmark, specifically tailored to evaluate registration methods for scenarios involving large rotations. UMERegRobust achieves better than state-of-the-art performance on the KITTI benchmark, especially when strict precision of (1{\deg}, 10cm) is considered (with an average gain of +9%), and notably outperform SOTA methods on the RotKITTI benchmark (with +45% gain compared the most recent SOTA method).