Decision PCR: Decision version of the Point Cloud Registration task

TL;DR

This paper introduces a deep learning-based classifier for the Decision Point Cloud Registration task, significantly improving registration performance in low-overlap scenarios and establishing a new state-of-the-art on challenging benchmarks.

Contribution

It presents the first deep learning framework for the Decision PCR task, enhancing existing registration methods and demonstrating strong generalization across datasets.

Findings

Achieved a new SOTA registration recall of 86.97% on 3DLoMatch.

Improved registration performance when integrated with existing methods.

Demonstrated strong generalization on outdoor ETH dataset.

Abstract

Low-overlap point cloud registration (PCR) remains a significant challenge in 3D vision. Traditional evaluation metrics, such as Maximum Inlier Count, become ineffective under extremely low inlier ratios. In this paper, we revisit the registration result evaluation problem and identify the Decision version of the PCR task as the fundamental problem. To address this Decision PCR task, we propose a data-driven approach. First, we construct a corresponding dataset based on the 3DMatch dataset. Then, a deep learning-based classifier is trained to reliably assess registration quality, overcoming the limitations of traditional metrics. To our knowledge, this is the first comprehensive study to address this task through a deep learning framework. We incorporate this classifier into standard PCR pipelines. When integrated with our approach, existing state-of-the-art PCR methods exhibit significantly enhanced registration performance. For example, combining our framework with GeoTransformer achieves a new SOTA registration recall of 86.97\% on the challenging 3DLoMatch benchmark. Our method also demonstrates strong generalization capabilities on the unseen outdoor ETH dataset.