SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation
Fan, Siqi1,2; Dong, Qiulei2,3,4; Zhu, Fenghua1; Lv, Yisheng1; Ye, Peijun1; Wang, Feiyue1
2021-06
Conference NameIEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Source PublicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Pages14499-14508
Conference Date2021-6-19
Conference PlaceOnline
Author of SourceIEEE ; IEEE Comp Soc ; CVF
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 dualdistance 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.

DOI10.1109/CVPR46437.2021.01427
URL查看原文
Indexed ByEI
Language英语
WOS Research AreaComputer Science ; Imaging Science & Photographic Technology
WOS SubjectComputer Science, Artificial IntelligenceImaging Science & Photographic Technology
WOS IDWOS:000742075004070
Citation statistics
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48725
Collection复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
Corresponding AuthorDong, Qiulei; Lv, Yisheng
Affiliation1.State Key Laboratory for Management and Control of Complex Systems, CASIA
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.National Laboratory of Pattern Recognition, CASIA
4.Center for Excellence in Brain Science and Intelligence Technology, CAS
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Fan, Siqi,Dong, Qiulei,Zhu, Fenghua,et al. SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation[C]//IEEE, IEEE Comp Soc, CVF,2021:14499-14508.
Files in This Item: Download All
File Name/Size DocType Version Access License
SCF-Net_Learning_Spa(4245KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fan, Siqi]'s Articles
[Dong, Qiulei]'s Articles
[Zhu, Fenghua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fan, Siqi]'s Articles
[Dong, Qiulei]'s Articles
[Zhu, Fenghua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fan, Siqi]'s Articles
[Dong, Qiulei]'s Articles
[Zhu, Fenghua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: SCF-Net_Learning_Spatial_Contextual_Features_for_Large-Scale_Point_Cloud_Segmentation_CVPR_2021_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.