Group-in-Group Relation-Based Transformer for 3D Point Cloud Learning

被引:7
作者
Liu, Shaolei [1 ,2 ]
Fu, Kexue [1 ,2 ]
Wang, Manning [1 ,2 ]
Song, Zhijian [1 ,2 ]
机构
[1] Shanghai Key Lab Med Image Comp & Comp Assisted I, Shanghai 200030, Peoples R China
[2] Fudan Univ, Digital Med Res Ctr, Sch Basic Med Sci, Shanghai 200032, Peoples R China
基金
中国国家自然科学基金;
关键词
3D point clouds; transformer; deep learning; point cloud classification; point cloud segmentation; NETWORK;
D O I
10.3390/rs14071563
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Deep point cloud neural networks have achieved promising performance in remote sensing applications, and the prevalence of Transformer in natural language processing and computer vision is in stark contrast to underexplored point-based methods. In this paper, we propose an effective transformer-based network for point cloud learning. To better learn global and local information, we propose a group-in-group relation-based transformer architecture to learn the relationships between point groups to model global information and between points within each group to model local semantic information. To further enhance the local feature representation, we propose a Radius Feature Abstraction (RFA) module to extract radius-based density features characterizing the sparsity of local point clouds. Extensive evaluation on public benchmark datasets demonstrate the effectiveness and competitive performance of our proposed method on point cloud classification and part segmentation.
引用
收藏
页数:11
相关论文
共 47 条
[1]   DGCNN: A convolutional neural network over large-scale labeled graphs [J].
Anh Viet Phan ;
Minh Le Nguyen ;
Yen Lam Hoang Nguyen ;
Lam Thu Bui .
NEURAL NETWORKS, 2018, 108 :533-543
[2]   Point Convolutional Neural Networks by Extension Operators [J].
Atzmon, Matan ;
Maron, Haggai ;
Lipman, Yaron .
ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (04)
[3]  
Ba J. L., 2016, Advances in Neural Information Processing Systems (NeurIPS), P1
[4]   Pointwise Convolutional Neural Networks [J].
Binh-Son Hua ;
Minh-Khoi Tran ;
Yeung, Sai-Kit .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :984-993
[5]  
Brown TB, 2020, ADV NEUR IN, V33
[6]   Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis [J].
Dai, Angela ;
Qi, Charles Ruizhongtai ;
Niessner, Matthias .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :6545-6554
[7]  
Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171
[8]  
Dosovitskiy A, 2020, ARXIV
[9]   Structural Relational Reasoning of Point Clouds [J].
Duan, Yueqi ;
Zheng, Yu ;
Lu, Jiwen ;
Zhou, Jie ;
Tian, Qi .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :949-958
[10]   GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition [J].
Feng, Yifan ;
Zhang, Zizhao ;
Zhao, Xibin ;
Ji, Rongrong ;
Gao, Yue .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :264-272