Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

Abstract

We propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points. We argue that the organization of 3D point clouds can be efficiently captured by a structure called superpoint graph (SPG), derived from a partition of the scanned scene into geometrically homogeneous elements. SPGs offer a compact yet rich representation of contextual relationships between object parts, which is then exploited by a graph convolutional network. Our framework sets a new state of the art for segmenting outdoor LiDAR scans (+11.9 and +8.8 mIoU points for both Semantic3D test sets), as well as indoor scans (+12.4 mIoU points for the S3DIS dataset).
Fichier principal
Vignette du fichier
1711.09869.pdf (6.73 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01801186 , version 1 (28-05-2018)

Identifiers

  • HAL Id : hal-01801186 , version 1

Cite

Loic Landrieu, Simonovsky Martin. Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs. 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018), Jun 2018, Salt Lake City, United States. ⟨hal-01801186⟩
1097 View
498 Download

Share

Gmail Facebook X LinkedIn More