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. 多模态人工智能系统全国重点实验室
  5. 机器人视觉团队
Language-Level Semantics-Conditioned 3D Point Cloud Segmentation

文献类型：期刊论文

作者Liu, Bo1; Zeng, Hui2,3; Dong, Qiulei1; Hu, Zhanyi1
刊名REMOTE SENSING
出版日期2024-07-01
卷号16期号:13页码:24
关键词three-dimensional point cloud semantic segmentation zero-shot learning
DOI10.3390/rs16132376
通讯作者Zeng, Hui(hzeng@ustb.edu.cn)
英文摘要In this work, a language-level Semantics-Conditioned framework for 3D Point cloud segmentation, called SeCondPoint, is proposed, where language-level semantics are introduced to condition the modeling of the point feature distribution, as well as the pseudo-feature generation, and a feature-geometry-based Mixup approach is further proposed to facilitate the distribution learning. Since a large number of point features could be generated from the learned distribution thanks to the semantics-conditioned modeling, any existing segmentation network could be embedded into the proposed framework to boost its performance. In addition, the proposed framework has the inherent advantage of dealing with novel classes, which seems an impossible feat for the current segmentation networks. Extensive experimental results on two public datasets demonstrate that three typical segmentation networks could achieve significant improvements over their original performances after enhancement by the proposed framework in the conventional 3D segmentation task. Two benchmarks are also introduced for a newly introduced zero-shot 3D segmentation task, and the results also validate the proposed framework.
资助项目National Natural Science Foundation of China[62273034] ; National Natural Science Foundation of China[U1805264] ; National Natural Science Foundation of China[62376269] ; Scientific and Technological Innovation Foundation of Foshan[BK21BF004]
WOS研究方向Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001269317600001
出版者MDPI
资助机构National Natural Science Foundation of China ; Scientific and Technological Innovation Foundation of Foshan
源URL[http://ir.ia.ac.cn/handle/173211/59233]  
专题自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者Zeng, Hui
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Sci & Technol Beijing, Beijing Engn Res Ctr Ind Spectrum Imaging, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
3.Univ Sci & Technol Beijing, Shunde Innovat Sch, Foshan 528399, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Bo,Zeng, Hui,Dong, Qiulei,et al. Language-Level Semantics-Conditioned 3D Point Cloud Segmentation[J]. REMOTE SENSING,2024,16(13):24.
APA Liu, Bo,Zeng, Hui,Dong, Qiulei,&Hu, Zhanyi.(2024).Language-Level Semantics-Conditioned 3D Point Cloud Segmentation.REMOTE SENSING,16(13),24.
MLA Liu, Bo,et al."Language-Level Semantics-Conditioned 3D Point Cloud Segmentation".REMOTE SENSING 16.13(2024):24.

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。