Please use this identifier to cite or link to this item:
Title: Multi-path region mining for weakly supervised 3D semantic segmentation on point clouds
Authors: Wei, Jiacheng
Lin, Guosheng
Yap, Kim-Hui
Hung, Tzu-Yi
Xie, Lihua
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Wei, J., Lin, G., Yap, K.-H., Hung, T.-Y., & Xie, L. (2020). Multi-path region mining for weakly supervised 3D semantic segmentation on point clouds. Proceedings of 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/CVPR42600.2020.00444
Project: AISG-RP-2018-003 
RG22/19 (S) 
Abstract: Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large scale 3D dataset is no longer a cumbersome process. However, manually producing point-level label on the large scale dataset is time and labor-intensive. In this paper, we propose a weakly supervised approach to predict point-level results using weak labels on 3D point clouds. We introduce our multi-path region mining module to generate pseudo point-level labels from a classification network trained with weak labels. It mines the localization cues for each class from various aspects of the network feature using different attention modules. Then, we use the point-level pseudo label to train a point cloud segmentation network in a fully supervised manner. To the best of our knowledge, this is the first method that uses cloud-level weak labels on raw 3D space to train a point cloud semantic segmentation network. In our setting, the 3D weak labels only indicate the classes that appeared in our input sample. We discuss both scene- and subcloud-level weakly labels on raw 3D point cloud data and perform in-depth experiments on them. On ScanNet dataset, our result trained with subcloud-level labels is compatible with some fully supervised methods.
DOI: 10.1109/CVPR42600.2020.00444
Rights: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
jiacheng 05495.pdf2.37 MBAdobe PDFThumbnail

Citations 10

Updated on Mar 14, 2023

Web of ScienceTM
Citations 10

Updated on Mar 15, 2023

Page view(s)

Updated on Mar 21, 2023

Download(s) 50

Updated on Mar 21, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.