English

Contrastive Learning for Joint Normal Estimation and Point Cloud Filtering

Computer Vision and Pattern Recognition 2023-05-04 v2

Abstract

Point cloud filtering and normal estimation are two fundamental research problems in the 3D field. Existing methods usually perform normal estimation and filtering separately and often show sensitivity to noise and/or inability to preserve sharp geometric features such as corners and edges. In this paper, we propose a novel deep learning method to jointly estimate normals and filter point clouds. We first introduce a 3D patch based contrastive learning framework, with noise corruption as an augmentation, to train a feature encoder capable of generating faithful representations of point cloud patches while remaining robust to noise. These representations are consumed by a simple regression network and supervised by a novel joint loss, simultaneously estimating point normals and displacements that are used to filter the patch centers. Experimental results show that our method well supports the two tasks simultaneously and preserves sharp features and fine details. It generally outperforms state-of-the-art techniques on both tasks. Our source code is available at https://github.com/ddsediri/CLJNEPCF.

Keywords

Cite

@article{arxiv.2208.06811,
  title  = {Contrastive Learning for Joint Normal Estimation and Point Cloud Filtering},
  author = {Dasith de Silva Edirimuni and Xuequan Lu and Gang Li and Antonio Robles-Kelly},
  journal= {arXiv preprint arXiv:2208.06811},
  year   = {2023}
}

Comments

This paper has been accepted to the IEEE TVCG journal. Our source code is available at https://github.com/ddsediri/CLJNEPCF

R2 v1 2026-06-25T01:41:45.415Z