文章基本信息

标题：Attention-Based Joint Semantic-Instance Segmentation of 3D Point Clouds
本地全文：下载
作者：HAO, W. ; WANG, H. ; LIANG, W. 等
期刊名称：Advances in Electrical and Computer Engineering
印刷版ISSN：1582-7445
电子版ISSN：1844-7600
出版年度：2022
卷号：22
期号：2
页码：19-28
DOI：10.4316/AECE.2022.02003
语种：English
出版社：Universitatea "Stefan cel Mare" Suceava
摘要：In this paper, we propose an attention-based instance and semantic segmentation joint approach, termed ABJNet, for addressing the instance and semantic segmentation of 3D point clouds simultaneously. First, a point feature enrichment (PFE) module is used to enrich the segmentation network’s input data by indicating the relative importance of each point’s neighbors. Then, a more efficient attention pooling operation is designed to establish a novel module for extracting point cloud features. Finally, an efficient attention-based joint segmentation module (ABJS) is proposed for combining semantic features and instance features in order to improve both segmentation tasks. We evaluate the proposed attention-based joint semantic-instance segmentation neural network (ABJNet) on a variety of indoor scene datasets, including S3DIS and ScanNet V2. Experimental results demonstrate that our method outperforms the start-of-the-art method in 3D instance segmentation and significantly outperforms it in 3D semantic segmentation.
关键词：Index Terms—computer graphics;object segmentation; feature extraction;pattern recognition;machine learning.