A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic Segmentation

Jiawei Han, Kaiqi Liu*, Wei Li, Guangzhi Chen, Wenguang Wang, Feng Zhang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

To significantly enhance the performance of point cloud semantic segmentation, this manuscript presents a novel method for constructing large-scale networks and offers an effective lightweighting technique. First, a latent point feature processing (LPFP) module is utilized to interconnect base networks such as PointNet++ and Point Transformer. This intermediate module serves both as a feature information transfer and a ground truth supervision function. Furthermore, in order to alleviate the increase in computational costs brought by constructing large-scale networks and better adapt to the demand for terminal deployment, a novel point cloud lightweighting method for semantic segmentation network (PCLN) is proposed to compress the network by transferring multidimensional feature information of large-scale networks. Specifically, at different stages of the large-scale network, the structure and attention information of the point features are selectively transferred to guide the compressed network to train in the direction of the large-scale network. This paper also solves the problem of representing global structure information of large-scale point clouds through feature sampling and aggregation. Extensive experiments on public datasets and real-world data demonstrate that the proposed method can significantly improve the performance of different base networks and outperform the state-of-the-art.

Original languageEnglish
Pages (from-to)2004-2017
Number of pages14
JournalIEEE Transactions on Image Processing
Volume33
DOIs
Publication statusPublished - 2024

Keywords

  • Point cloud semantic segmentation
  • information combination
  • large-scale network
  • lightweighting technique

Fingerprint

Dive into the research topics of 'A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic Segmentation'. Together they form a unique fingerprint.

Cite this