Objformer: Boosting 3D object detection via instance-wise interaction

doi:10.1016/j.patcog.2023.110061

CORC > 自动化研究所 > 中国科学院自动化研究所 > 紫东太初大模型研究中心

	Objformer: Boosting 3D object detection via instance-wise interaction
	Tao, Manli 1,2; Zhao, Chaoyang 1,3,4; Tang, Ming 1,2; Wang, Jinqiao 1,2,4
刊名	PATTERN RECOGNITION
	2024-02-01
卷号	146 页码:9
关键词	3D object detection Point clouds Incompletion and occlusion Instance-wise interaction
ISSN号	0031-3203
DOI	10.1016/j.patcog.2023.110061
通讯作者	Zhao, Chaoyang(chaoyang.zhao@nlpr.ia.ac.cn)
英文摘要	Deep learning on point clouds drives 3D object detection. Despite rapid progress, point-based methods still suffer from the problems such as incompletion and occlusion, which are caused by the material properties of objects and cluttered scenes. These difficult targets increase the difficulty of identification or even lead to misidentification, severely weakening the performance of point-based methods on 3D object detection. To alleviate the above problems, we propose the Objformer to boost point-based 3D object detection via instance -wise interaction. We design an instance feature encoder to encode clean instance features, which contain key geometric priors and holistic semantic information. Further, an instance interaction module is devised to aggregate the complementary features across instances with label-guided interaction, boosting the performance of the 3D object detection. Experiments show that Objformer outperforms previous point-based state-of-the -arts on two popular benchmarks, ScanNet V2 and SUN RGB-D. Especially, our single-modal Objformer even outperforms the competing advanced multi-modal fusion method on both SUN RGB-D and ScanNet V2.
资助项目	Key-Area Research and Development Program of Guangdong Province[2021B0101410003] ; National Natural Science Foundation of China[61976210] ; National Natural Science Foundation of China[62176254] ; National Natural Science Foundation of China[62006230] ; National Natural Science Foundation of China[62002357] ; National Natural Science Foundation of China[61876086]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:001103462700001
资助机构	Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/55213]
专题	紫东太初大模型研究中心
通讯作者	Zhao, Chaoyang
作者单位	1.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, 19 A Yuquan Rd, Beijing 100049, Peoples R China 3.Dev Res Inst Guangzhou Smart City, Guangzhou, Peoples R China 4.ObjectEye Inc, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Tao, Manli,Zhao, Chaoyang,Tang, Ming,et al. Objformer: Boosting 3D object detection via instance-wise interaction[J]. PATTERN RECOGNITION,2024,146:9.
APA	Tao, Manli,Zhao, Chaoyang,Tang, Ming,&Wang, Jinqiao.(2024).Objformer: Boosting 3D object detection via instance-wise interaction.PATTERN RECOGNITION,146,9.
MLA	Tao, Manli,et al."Objformer: Boosting 3D object detection via instance-wise interaction".PATTERN RECOGNITION 146(2024):9.