Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

Haoran Zhou, Honghua Chen, Yingkui Zhang, Mingqiang Wei, Haoran Xie, Jun Wang, Tong Lu, Jing Qin, Xiao Ping Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate normals for noisy point clouds. Traditional normal estimation wisdom heavily depends on priors such as surface shapes or noise distributions, while learning-based solutions settle for single types of hand-crafted features. Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations. To this end, several feature modules are developed and incorporated into Refine-Net by a novel connection module. Besides the overall network architecture of Refine-Net, we propose a new multi-scale fitting patch selection scheme for the initial normal estimation, by absorbing geometry domain knowledge. Also, Refine-Net is a generic normal estimation framework: 1) point normals obtained from other methods can be further refined, and 2) any feature module related to the surface geometric structures can be potentially integrated into the framework. Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets.

Original languageEnglish
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
DOIs
Publication statusAccepted/In press - 2022

Keywords

  • Estimation
  • Feature extraction
  • multi-scale and -feature modules
  • Noise measurement
  • noisy point clouds
  • normal estimation
  • Point cloud compression
  • point cloud denoising
  • Refine-Net
  • Surface reconstruction
  • Task analysis
  • Three-dimensional displays

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds'. Together they form a unique fingerprint.

Cite this