arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.02104cs.CV
收藏

点判别学习用于数据高效的3D点云分析

Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis

Institute for Infocomm Research, A*STAR(新加坡科技研究局资讯通信研究院);Nanyang Technological University(南洋理工大学);Centre for Frontier AI Research, A*STAR(新加坡科技研究局前沿人工智能研究中心);University of Cambridge(剑桥大学)

Fayao Liu, Guosheng Lin, Chuan-Sheng Foo, Chaitanya K. Joshi, Jie Lin

摘要:

三维点云分析因其广泛的应用而引起了人们的广泛关注。然而,收集大量标记的3D点云数据既耗时又耗力。这需要数据高效的学习方法。在这项工作中,我们提出了PointDisc,这是一种点判别学习方法,可以利用自我监督进行数据高效的3D点云分类和分割。PointDisc对骨干网络产生的中间和全局级特征施加了一种新的点区分损失。该点辨别损失强制学习特征与属于相应局部形状区域的点一致,并且与随机采样的噪声点不一致。我们对3D对象分类,3D语义和部分分割进行了广泛的实验,显示了PointDisc在数据高效学习方面的优势。详细的分析表明,PointDisc学习无监督的特征,可以很好地捕捉局部和全局几何。

英文摘要:

3D point cloud analysis has drawn a lot of research attention due to its wide applications. However, collecting massive labelled 3D point cloud data is both time-consuming and labor-intensive. This calls for data-efficient learning methods. In this work we propose PointDisc, a point discriminative learning method to leverage self-supervisions for data-efficient 3D point cloud classification and segmentation. PointDisc imposes a novel point discrimination loss on the middle and global level features produced by the backbone network. This point discrimination loss enforces learned features to be consistent with points belonging to the corresponding local shape region and inconsistent with randomly sampled noisy points. We conduct extensive experiments on 3D object classification, 3D semantic and part segmentation, showing the benefits of PointDisc for data-efficient learning. Detailed analysis demonstrate that PointDisc learns unsupervised features that well capture local and global geometry.

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。

↑