Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

Abstract

Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate in the 2D image space. Direct semantic segmentation of unstructured 3D point clouds is still an open research problem. The recently proposed PointNet architecture presents an interesting step ahead in that it can operate on unstructured point clouds, achieving encouraging segmentation results. However, it subdivides the input points into a grid of blocks and processes each such block individually. In this paper, we investigate the question how such an architecture can be extended to incorporate larger-scale spatial context. We build upon PointNet and propose two extensions that enlarge the receptive field over the 3D scene. We evaluate the proposed strategies on challenging indoor and outdoor datasets and show improved results in both scenarios.

References in corpus (1)

• SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction

Cited by in corpus (11)

• Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation
• DeepGCNs: Making GCNs Go as Deep as CNNs
• Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook
• AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
• A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation
• PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stage
• PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models
• Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey
• Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
• Multi-view Incremental Segmentation of 3D Point Clouds for Mobile Robots
• ImaginateAR: AI-Assisted In-Situ Authoring in Augmented Reality