3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation

doi:10.1007/978-3-030-01234-2_25

	3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation
	Ye, Xiaoqing 1,2; Li, Jiamao 1; Huang, Hexiao 3; Du, Liang 1,2; Zhang, Xiaolin 1
	2018
会议名称	15th European Conference on Computer Vision (ECCV)
会议录名称	SPRINGER INTERNATIONAL PUBLISHING AG
页码	415-430
会议日期	SEP 08-14, 2018
会议地点	Munich, GERMANY
出版地	CHAM
摘要	Semantic segmentation of 3D unstructured point clouds remains an open research problem. Recent works predict semantic labels of 3D points by virtue of neural networks but take limited context knowledge into consideration. In this paper, a novel end-to-end approach for unstructured point cloud semantic segmentation, named 3P-RNN, is proposed to exploit the inherent contextual features. First the efficient point-wise pyramid pooling module is investigated to capture local structures at various densities by taking multi-scale neighborhood into account. Then the two-direction hierarchical recurrent neural networks (RNNs) are utilized to explore long-range spatial dependencies. Each recurrent layer takes as input the local features derived from unrolled cells and sweeps the 3D space along two directions successively to integrate structure knowledge. On challenging indoor and outdoor 3D datasets, the proposed framework demonstrates robust performance superior to state-of-the-arts.
关键词	3D semantic segmentation Unstructured point cloud Recurrent neural networks Pointwise pyramid pooling
DOI	10.1007/978-3-030-01234-2_25
收录类别	CPCI-S
语种	英语
WOS研究方向	Computer Science ; Imaging Science & Photographic Technology
WOS类目	Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology
WOS记录号	WOS:000594221500025
原始文献类型	Proceedings Paper
引用统计	被引频次：156[WOS] [WOS记录] [WOS相关记录]
文献类型	会议论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/168810
专题	国家开放大学上海分部
通讯作者	Li, Jiamao
作者单位	1.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Shanghai, Peoples R China; 2.Univ Chinese Acad Sci, Beijing, Peoples R China; 3.Shanghai Open Univ, Sch Sci & Technol, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Ye, Xiaoqing,Li, Jiamao,Huang, Hexiao,et al. 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation[C]. CHAM,2018:415-430.