Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation | |
Deng, Shuang1,2,3; Liu, Bo1,2,3; Dong, Qiulei1,2,3; Hu, Zhanyi2,3 | |
2021-07 | |
会议日期 | 2021-6 |
会议地点 | Shenzhen, China |
英文摘要 | Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide an insight into spatial manipulation modules. Firstly, we find that the smaller the rotational degree of freedom (RDF) of objects is, the more easily these objects are handled by these DNNs. Then, we investigate the effect of the popular T-Net module and find that it could not reduce the RDF of objects. Motivated by the above two issues, we propose a rotation transformation network for point cloud analysis, called RTN, which could reduce the RDF of input 3D objects to 0. The RTN could be seamlessly inserted into many existing DNNs for point cloud analysis. Extensive experimental results on 3D point cloud classification and segmentation tasks demonstrate that the proposed RTN could improve the performances of several state-of-the-art methods significantly. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/49907] |
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 | Dong, Qiulei |
作者单位 | 1.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, China 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China |
推荐引用方式 GB/T 7714 | Deng, Shuang,Liu, Bo,Dong, Qiulei,et al. Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation[C]. 见:. Shenzhen, China. 2021-6. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论