RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registration

TL;DR

This paper introduces RGBD-Glue, a new feature combination framework for RGB-D point cloud registration that effectively leverages both visual and geometric features, overcoming individual weaknesses to improve registration accuracy.

Contribution

It proposes a looser, more effective feature combination method with a transformation consistency filter and adaptive threshold, applicable to various feature descriptors for improved registration.

Findings

Achieves state-of-the-art performance on ScanNet and 3DMatch datasets.

Effectively combines visual and geometric features to improve registration accuracy.

Overcomes limitations of deep feature fusion methods.

Abstract

Point cloud registration is a fundamental task for estimating rigid transformations between point clouds. Previous studies have used geometric information for extracting features, matching and estimating transformation. Recently, owing to the advancement of RGB-D sensors, researchers have attempted to combine visual and geometric information to improve registration performance. However, these studies focused on extracting distinctive features by deep feature fusion, which cannot effectively solve the negative effects of each feature's weakness, and cannot sufficiently leverage the valid information. In this paper, we propose a new feature combination framework, which applies a looser but more effective combination. An explicit filter based on transformation consistency is designed for the combination framework, which can overcome each feature's weakness. And an adaptive threshold determined by the error distribution is proposed to extract more valid information from the two types of features. Owing to the distinctive design, our proposed framework can estimate more accurate correspondences and is applicable to both hand-crafted and learning-based feature descriptors. Experiments on ScanNet and 3DMatch show that our method achieves a state-of-the-art performance.