DKGCN-PCR: Deformable Kernel Graph Convolutional Network for Point Cloud Registration

Yuandong Niu, Juntao Ma, Lin Shi, Yunfeng Jiang, Ting An, Zhaorui Li, Zhengguo LiJournal of the European Optical Society Rapid Publications 2025 · DOI

Abstract

We study the problem of feature extraction in point cloud registration. Traditional point clouds has the characteristic of irregular structure, which causes the neighborhood relationship that cannot effectively obtain point cloud data, and increases the difficulty of feature extraction in the point cloud registration task. This paper proposes a graph convolution point cloud registration network based on a deformable kernel. Compared with the non-deformable kernel, the proposed network is more suitable for irregular and unstructured point cloud data. Meanwhile, the network uses the semantic residual module to restore the lost local information and enhance the integrity of feature expression. The feature fusion layer integrates global and local features to enhance the model’s ability to express the features of complex point cloud data. We conducted tests on the 3DMatch, 3DLoMatch, and KITTI datasets to verify the effectiveness of the algorithm.
BibTeX
@article{niu2025dkgcn,
  author = {Yuandong Niu and Yuandong Niu and Juntao Ma and Lin Shi and Yunfeng Jiang and Ting An and Ting An and Zhaorui Li and Zhengguo Li},
  title = {{DKGCN-PCR: Deformable Kernel Graph Convolutional Network for Point Cloud Registration}},
  journal = {Journal of the European Optical Society Rapid Publications},
  year = {2025},
  doi = {10.1051/jeos/2025035},
}

Loading related content...

Figure