中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 紫东太初大模型研究中心
Objformer: Boosting 3D object detection via instance-wise interaction

文献类型：期刊论文

作者Tao, Manli1,2; Zhao, Chaoyang1,3,4; Tang, Ming1,2; Wang, Jinqiao1,2,4
刊名PATTERN RECOGNITION
出版日期2024-02-01
卷号146页码:9
ISSN号0031-3203
关键词3D object detection Point clouds Incompletion and occlusion Instance-wise interaction
DOI10.1016/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
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。