Spherical Interpolated Convolutional Network With Distance–Feature Density for 3-D Semantic Segmentation of Point Clouds
- 8 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 52 (12) , 13546-13556
Abstract
The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3-D convolution kernel to extract features from raw 3-D point clouds because of the unstructured property of point clouds. In this article, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3-D convolution operator. In addition, this article analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance–feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of the spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3-D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. The comparison experiments with the traditional grid-shaped 3-D convolution operator demonstrated that the newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. The source codes will be released on https://github.com/IRMVLab/SIConv .Keywords
All Related Versions
Funding Information
- Natural Science Foundation of China (62073222, U1913204)
- Shanghai Municipal Education Commission and Shanghai Education Development Foundation (19SG08)
- Shenzhen Science and Technology Program (JSGG20201103094400002)
- Science and Technology Commission of Shanghai Municipality (21511101900)
- NVIDIA Corporation
This publication has 51 references indexed in Scilit:
- O-CNNACM Transactions on Graphics, 2017
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- OctNet: Learning Deep 3D Representations at High Resolutions2017
- A FORMAL PROOF OF THE KEPLER CONJECTUREForum of Mathematics, Pi, 2017
- Deep Residual Learning for Image Recognition2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- GNCCP—Graduated NonConvexityand Concavity ProcedureIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Introducing Memory and Association Mechanism Into a Biologically Inspired Visual ModelIEEE Transactions on Cybernetics, 2013
- Does the proof stack up?Nature, 2003