3DPCP-Net: A Lightweight Progressive 3D Correspondence Pruning Network for Accurate and Efficient Point Cloud Registration

Jingtao Wang, Zechao Li

Abstract: Accurately identifying correct correspondence (inlier) within initial ones is pivotal for robust feature-based point cloud registration. Current methods typically rely on one-shot 3D correspondence classification with a single coherence constraint to obtain inlier. These approaches are either insufficiently accurate or inefficient, often requiring more network parameters. To address this issue, we propose a lightweight network, 3DPCP-Net, for fast and robust registration. Its core design lies in progressive correspondence pruning through mining deep spatial geometric coherence, which can effectively learn pairwise 3D spatial distance and angular features to progressively remove outlier (mismatched correspondence) for accurate pose estimation. Moreover, we also propose an efficient feature-based hypothesis proposer that leverages the geometric consistency features to generate reliable model hypotheses for each reliable correspondence explicitly. Extensive experiments on 3DMatch, 3DLoMatch, KITTI and Augmented ICL-NUIM demonstrate the accurate and efficient of our method for outlier removal and pose estimation tasks. Furthermore, our method is highly versatile and can be easily integrated into both learning-based and geometry-based frameworks, enabling them to achieve state-of-the-art results. The code is provided in the supplementary materials.

Primary Subject Area: [Content] Media Interpretation

Secondary Subject Area: [Content] Multimodal Fusion

Relevance To Conference:

Point cloud registration, aligning multiple point clouds, is vital for multimedia/multimodal processing by enabling:
3D Scene Understanding: Combining point clouds from various viewpoints creates comprehensive 3D representations for applications like VR, AR, and 3D modeling.
Object Recognition and Tracking: Registration aids in identifying and tracking objects across frames or datasets, crucial for autonomous navigation and robotics.
Enhanced Data Fusion: Combining LiDAR with images or other sensors enriches environmental understanding for tasks like semantic segmentation.
Diverse Applications: Point cloud registration is essential for autonomous vehicles, robotics, cultural heritage preservation, and medical imaging.
By aligning 3D data, it unlocks a deeper understanding of the environment and facilitates advanced technologies across various domains.

Submission Number: 3370