Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

2017/11/27 by Landrieu, Loic, Simonovsky, Martin · 21 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1711.09869

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).

Cited by

• From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning
• LitePT: Lighter Yet Stronger Point Transformer
• EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation
• DenseScan: Advancing 3D Scene Understanding with 2D Dense Annotation
• MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding
• LMSeg: an end-to-end geometric message-passing network on barycentric dualgraphs for large-scale landscape mesh segmentation
• Deep Imbalanced Multi-Target Regression: 3D Point Cloud Voxel Content Estimation in Simulated Forests
• TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding
• 3D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinement
• Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
• ASIA: Adaptive 3D Segmentation using Few Image Annotations
• DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion
• OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction
• Deep learning-based 3D morphological segmentation and quantitative growth analysis of field-grown cabbage across the full cycle
• SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features
• Graph-based Point Cloud Surface Reconstruction using B-Splines
• RangeSAM: On the Potential of Visual Foundation Models for Range-View represented LiDAR segmentation
• OpenUrban3D: Annotation-Free Open-Vocabulary Semantic Segmentation of Large-Scale Urban Point Clouds
• SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing
• CitySeg: A 3D Open Vocabulary Semantic Segmentation Foundation Model in City-scale Scenarios
• Cross-Dataset Semantic Segmentation Performance Analysis: Unifying NIST Point Cloud City Datasets for 3D Deep Learning

Related

• Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning
• Rethinking 3D LiDAR Point Cloud Segmentation
• Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene
• Semantic Segmentation on 3D Point Clouds with High Density Variations
• Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation