Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
This addresses the problem of efficiently segmenting millions of points in 3D scans for applications like autonomous driving and robotics, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles semantic segmentation of large-scale point clouds by introducing superpoint graphs (SPGs) to capture contextual relationships, achieving state-of-the-art results with improvements of +11.9 and +8.8 mIoU on outdoor LiDAR scans and +12.4 mIoU on indoor scans.
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).