SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation
Authors:
Top Cited Papers
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 14499-14508
Abstract
How to learn effective features from large-scale point clouds for semantic segmentation has attracted increasing attention in recent years. Addressing this problem, we propose a learnable module that learns Spatial Contextual Features from large-scale point clouds, called SCF in this paper. The proposed module mainly consists of three blocks, including the local polar representation block, the dual-distance attentive pooling block, and the global contextual feature block. For each 3D point, the local polar representation block is firstly explored to construct a spatial representation that is invariant to the z-axis rotation, then the dual-distance attentive pooling block is designed to utilize the representations of its neighbors for learning more discriminative local features according to both the geometric and feature distances among them, and finally, the global contextual feature block is designed to learn a global context for each 3D point by utilizing its spatial location and the volume ratio of the neighborhood to the global point cloud. The proposed module could be easily embedded into various network architectures for point cloud segmentation, naturally resulting in a new 3D semantic segmentation network with an encoder-decoder architecture, called SCF-Net in this work. Extensive experimental results on two public datasets demonstrate that the proposed SCF-Net performs better than several state-of-the-art methods in most cases.Keywords
Funding Information
- National Natural Science Foundation of China
- Chinese Academy of Sciences
This publication has 33 references indexed in Scilit:
- Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods2018
- A structured regularization framework for spatially smoothing semantic labelings of 3D point cloudsISPRS Journal of Photogrammetry and Remote Sensing, 2017
- SEGCloud: Semantic Segmentation of 3D Point Clouds2017
- Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds2017
- 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds2017
- SEMANTIC3D.NET: A NEW LARGE-SCALE POINT CLOUD CLASSIFICATION BENCHMARKISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017
- Point cloud labeling using 3D Convolutional Neural Network2016
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- Contextual classification of lidar data and building object detection in urban areasISPRS Journal of Photogrammetry and Remote Sensing, 2014
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004