ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance

TL;DR

ViGG introduces a robust RGB-D point cloud registration approach that leverages mutual guidance between visual and geometric information, improving accuracy and robustness over existing methods across multiple datasets.

Contribution

The paper presents a novel mutual guidance strategy for RGB-D registration that combines visual and geometric cues to enhance robustness and accuracy, addressing limitations of prior methods.

Findings

Outperforms recent state-of-the-art methods on 3DMatch, ScanNet, and KITTI datasets.

Effective in both learning-free and learning-based registration scenarios.

Demonstrates superior robustness in noisy and ambiguous conditions.

Abstract

Point cloud registration is a fundamental task in 3D vision. Most existing methods only use geometric information for registration. Recently proposed RGB-D registration methods primarily focus on feature fusion or improving feature learning, which limits their ability to exploit image information and hinders their practical applicability. In this paper, we propose ViGG, a robust RGB-D registration method using mutual guidance. First, we solve clique alignment in a visual-geometric combination form, employing a geometric guidance design to suppress ambiguous cliques. Second, to mitigate accuracy degradation caused by noise in visual matches, we propose a visual-guided geometric matching method that utilizes visual priors to determine the search space, enabling the extraction of high-quality, noise-insensitive correspondences. This mutual guidance strategy brings our method superior robustness, making it applicable for various RGB-D registration tasks. The experiments on 3DMatch, ScanNet and KITTI datasets show that our method outperforms recent state-of-the-art methods in both learning-free and learning-based settings. Code is available at https://github.com/ccjccjccj/ViGG.