Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

Loic Landrieu (1) , Martin Simonovsky (2)

1 MATIS - Méthodes d'Analyses pour le Traitement d'Images et la Stéréorestitution
2 ENPC - École des Ponts ParisTech

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).

Domaines: Machine Learning [stat.ML]; Intelligence artificielle [cs.AI]

Loic Landrieu, Martin Simonovsky. Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs. CVPR 2018, IEEE Conference on Computer Vision and Pattern Recognition, Jun 2018, Salt Lake City, France. ⟨hal-02545223⟩