English

Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding

Computer Vision and Pattern Recognition 2022-07-05 v1

Abstract

Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this study, we propose a method that automatically learns to enhance/suppress edges while keeping the its working mechanism clear. First, we theoretically figure out how edge enhancement/suppression works. Second, we experimentally verify the edge enhancement/suppression behavior. Third, we empirically show that this behavior improves performance. In general, we observe that the proposed method achieves competitive performance in point cloud classification and segmentation tasks.

Keywords

Cite

@article{arxiv.2207.01174,
  title  = {Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding},
  author = {Haoyi Xiu and Xin Liu and Weimin Wang and Kyoung-Sook Kim and Takayuki Shinohara and Qiong Chang and Masashi Matsuoka},
  journal= {arXiv preprint arXiv:2207.01174},
  year   = {2022}
}