CRNet: Cross-Reconstruction Network for Inconsistent Point Cloud Registration

Yunzhe Xiao, Xueqiong Li, Shaowu Yang, Wenjing Yang, Yong DouICME 2024 · OpenReview

Abstract

Deep learning methods have made significant advancements in point cloud registration, achieving excellent performance on consistent point clouds. However, these methods face challenges when dealing with point clouds exhibiting inconsistent spatial distributions. To address this issue, we propose the Cross-Reconstruction Network (CRNet), a novel approach designed to register two inconsistent point clouds by reconstructing them into a consistent shape. CRNet utilizes a cross-learning framework that facilitates feature interaction between input point clouds at both global and point-wise levels. This interaction network enables the bidirectional generation of corresponding points to reconstruct consistent point clouds for transformation estimation. Furthermore, the transformation parameters can be refined by a regression network to achieve more accurate registration. The experimental results valuated on benchmark datasets demonstrate that CRNet outperforms state-of-the-art methods in inconsistent scenarios.
BibTeX
@inproceedings{xiao2024crnet,
  author = {Yunzhe Xiao and Xueqiong Li and Shaowu Yang and Wenjing Yang and Yong Dou},
  title = {{CRNet: Cross-Reconstruction Network for Inconsistent Point Cloud Registration}},
  booktitle = {ICME},
  year = {2024},
  url = {https://openreview.net/forum?id=Oqu8oJKPKR},
}

Loading related content...

Figure