arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.01174cs.CV
收藏

利用扩散增强局部特征学习实现三维点云理解

Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding

Tokyo Institute of Technology(东京工业大学);Artificial Intelligence Research Center, AIST(产业技术综合研究所人工智能研究中心);Dalian University of Technology(大连理工大学);PASCO Corporation(PASCO公司)

Haoyi Xiu, Xin Liu, Weimin Wang, Kyoung-Sook Kim, Takayuki Shinohara, Qiong Chang, Masashi Matsuoka

摘要:

由于缺乏连接信息,学习点云是具有挑战性的,即,边缘.虽然现有的边缘感知方法可以通过对边缘进行建模来提高性能,但边缘如何有助于提高性能还不清楚。在这项研究中,我们提出了一种自动学习增强/抑制边缘的方法,同时保持其工作机制清晰。首先,我们从理论上弄清楚边缘增强/抑制是如何工作的。其次,我们实验验证的边缘增强/抑制行为。第三,我们的经验表明,这种行为提高了性能。在一般情况下,我们观察到所提出的方法在点云分类和分割任务中实现了有竞争力的性能。

英文摘要:

Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this study, we propose a method that automatically learns to enhance/suppress edges while keeping the its working mechanism clear. First, we theoretically figure out how edge enhancement/suppression works. Second, we experimentally verify the edge enhancement/suppression behavior. Third, we empirically show that this behavior improves performance. In general, we observe that the proposed method achieves competitive performance in point cloud classification and segmentation tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑