Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

Loic Landrieu, Martin Simonovsky
11/27/2017
cs.CVcs.LGcs.NE

Official code: loicland/superpoint_graph (801 stars, MIT, PyTorch, last commit 2023-07-19).

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).

View on arXivView PDF

Code Implementations(1)

loicland/superpoint_graphOfficial100%
PyTorchMIT

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

801215C++, CMakeNov 22, 20173 years agoMIT
clusteringlarge-scalelidarpartitionply-files+6 more

Similar Papers

Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework

88% match1 repo232023

RESSCAL3D: Resolution Scalable 3D Semantic Segmentation of Point Clouds

87% match2024

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

87% match1 repo8012019

Efficiently Expanding Receptive Fields: Local Split Attention and Parallel Aggregation for Enhanced Large-scale Point Cloud Semantic Segmentation

87% match2024

Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene

86% match1 repo162023

Deep Learning-Based 3D Instance and Semantic Segmentation: A Review

86% match2024

Cite this paper

@article{landrieu2017largescale,
  title  = {Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs},
  author = {Loic Landrieu and Martin Simonovsky},
  year   = {2017},
  eprint = {1711.09869},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1711.09869}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1711.09869.svg)](https://codeofpaper.com/paper/1711.09869)

Discussion