SAF-Nets: Shape-Adaptive Filter Networks for 3D point cloud processing

Seon Ho Lee, Chang Su Kim

Research output: Contribution to journalArticlepeer-review

Abstract

A deep learning framework for 3D point cloud processing is proposed in this work. In a point cloud, local neighborhoods have various shapes, and the semantic meaning of each point is determined within the local shape context. Thus, we propose shape-adaptive filters (SAFs), which are dynamically generated from the distributions of local points. The proposed SAFs can extract robust features against noise or outliers, by employing local shape contexts to suppress them. Also, we develop the SAF-Nets for classification and segmentation using multiple SAF layers. Extensive experimental results demonstrate that the proposed SAF-Nets significantly outperform the state-of-the-art conventional algorithms on several benchmark datasets. Moreover, it is shown that SAFs can improve scene flow estimation performance as well.

Original languageEnglish
Article number103246
JournalJournal of Visual Communication and Image Representation
Volume79
DOIs
Publication statusPublished - 2021 Aug

Keywords

  • Deep learning
  • Point cloud processing
  • Shape-adaptive filter

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'SAF-Nets: Shape-Adaptive Filter Networks for 3D point cloud processing'. Together they form a unique fingerprint.

Cite this