GECNN for Weakly Supervised Semantic Segmentation of 3D Point Clouds
- 1 December 2021
- journal article
- research article
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E104.D (12), 2237-2243
- https://doi.org/10.1587/transinf.2021edp7134
Abstract
This paper presents a novel method for weakly supervised semantic segmentation of 3D point clouds using a novel graph and edge convolutional neural network (GECNN) towards 1% and 10% point cloud with labels. Our general framework facilitates semantic segmentation by encoding both global and local scale features via a parallel graph and edge aggregation scheme. More specifically, global scale graph structure cues of point clouds are captured by a graph convolutional neural network, which is propagated from pairwise affinity representation over the whole graph established in a d-dimensional feature embedding space. We integrate local scale features derived from a dynamic edge feature aggregation convolutional neural networks that allows us to fusion both global and local cues of 3D point clouds. The proposed GECNN model is trained by using a comprehensive objective which consists of incomplete, inexact, self-supervision and smoothness constraints based on partially labeled points. The proposed approach enforces global and local consistency constraints directly on the objective losses. It inherently handles the challenges of segmenting sparse 3D point clouds with limited annotations in a large scale point cloud space. Our experiments on the ShapeNet and S3DIS benchmarks demonstrate the effectiveness of the proposed approach for efficient (within 20 epochs) learning of large scale point cloud semantics despite very limited labels.Keywords
This publication has 7 references indexed in Scilit:
- Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point CloudsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2020
- Dynamic Graph CNN for Learning on Point CloudsACM Transactions on Graphics, 2019
- KPConv: Flexible and Deformable Convolution for Point CloudsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Semantic Segmentation of 3D LiDAR Data in Dynamic Scene Using Semi-Supervised LearningIEEE Transactions on Intelligent Transportation Systems, 2019
- 3D Semantic Segmentation with Submanifold Sparse Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- WEAKLY SUPERVISED SEGMENTATION-AIDED CLASSIFICATION OF URBAN SCENES FROM 3D LIDAR POINT CLOUDSThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017
- A scalable active framework for region annotation in 3D shape collectionsACM Transactions on Graphics, 2016