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).
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01801186
Contributor : Simonovsky Martin <>
Submitted on : Monday, May 28, 2018 - 11:36:03 AM
Last modification on : Wednesday, October 9, 2019 - 4:34:03 PM
Long-term archiving on : Wednesday, August 29, 2018 - 1:22:06 PM

File

1711.09869.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01801186, version 1

Citation

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⟩

Share

Metrics

Record views

664

Files downloads

407