Semantic-Context Graph Network for Point-Based 3D Object Detection

doi:10.1109/TCSVT.2023.3271318

	Semantic-Context Graph Network for Point-Based 3D Object Detection
	Dong, Shuwei 1; Kong, Xiaoyu 2; Pan, Xingjia 3; Tang, Fan 4; Li, Wei 5; Chang, Yi 1; Dong, Weiming 6
	2023-11-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	33 期号:11 页码:6474-6486
摘要	Point-based indoor 3D object detection has received increasing attention with the large demand for augmented reality, autonomous driving, and robot technology in the industry. However, the detection precision suffers from inputs with semantic ambiguity, i.e., shape symmetries, occlusion, and texture missing, which would lead that different objects appearing similar from different viewpoints and then confusing the detection model. Typical point-based detectors relieve this problem via learning proposal representations with both geometric and semantic information, while the entangled representation may cause a reduction in both semantic and spatial discrimination. In this paper, we focus on alleviating the confusion from entanglement and then enhancing the proposal representation by considering the proposal's semantics and the context in one scene. A semantic-context graph network (SCGNet) is proposed, which mainly includes two modules: a category-aware proposal recoding module (CAPR) and a proposal context aggregation module (PCAg). To produce semantically clear features from entanglement representation, the CAPR module learns a high-level semantic embedding for each category to extract discriminative semantic clues. In view of further enhancing the proposal representation and leveraging the semantic clues, the PCAg module builds a graph to mine the most relevant context in the scene. With few bells and whistles, the SCGNet achieves SOTA performance and obtains consistent gains when applying to different backbones (0.9% similar to 2.4% on ScanNet V2 and 1.6% similar to 2.2% on SUN RGB-D for mAP@0.25). Code is available at https://github.com/dsw-jlurgzn/SCGNet.
关键词	3D object detection graph neural networks information entanglement
DOI	10.1109/TCSVT.2023.3271318
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[L221013] ; National Natural Science Foundation of China[62102162] ; National Natural Science Foundation of China[61832016] ; National Natural Science Foundation of China[62172126] ; National Natural Science Foundation of China[62106063] ; National Natural Science Foundation of China[61976102] ; National Natural Science Foundation of China[U20B2070] ; National Natural Science Foundation of China[U19A2065]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:001093434100020
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38104
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tang, Fan; Chang, Yi
作者单位	1.Jilin Univ, Sch Artificial Intelligence, Changchun 130012, Peoples R China 2.Harbin Inst Technol Shenzhen, Sch Comp Sci & Technol, Shenzhen 518055, Guangdong, Peoples R China 3.Momenta, Beijing 215100, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 5.Didiglobal, Beijing 100193, Peoples R China 6.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Dong, Shuwei,Kong, Xiaoyu,Pan, Xingjia,et al. Semantic-Context Graph Network for Point-Based 3D Object Detection[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2023,33(11):6474-6486.
APA	Dong, Shuwei.,Kong, Xiaoyu.,Pan, Xingjia.,Tang, Fan.,Li, Wei.,...&Dong, Weiming.(2023).Semantic-Context Graph Network for Point-Based 3D Object Detection.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,33(11),6474-6486.
MLA	Dong, Shuwei,et al."Semantic-Context Graph Network for Point-Based 3D Object Detection".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 33.11(2023):6474-6486.