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 2209.00949cs.CV
收藏

学习用于创建3D点云图形的特定于任务的功能

Learning task-specific features for 3D pointcloud graph creation

Universitat Politècnica de Catalunya(加泰罗尼亚理工大学)

Elías Abad-Rocamora, Javier Ruiz-Hidalgo

摘要:

使用深度学习方法处理3D点云并非易事。一个常见的选择是用图神经网络来做,但这个框架涉及到在点之间创建边,而这些点之间显然不相关。从历史上看,已经提出了简单的手工方法,如k最近邻(k-NN)或xyz特征上的查询球点,将更多的注意力集中在改善网络上,而不是改善图。在这项工作中,我们提出了一个更有原则的方式来创建一个图形从三维点云。我们的方法是基于对输入的3D点云的变换执行k-NN。这种转换是由具有可学习参数的多后期感知器(MLP)完成的,该参数通过与网络的其余部分联合进行反向传播来优化。我们还介绍了一种基于应力最小化的正则化方法,它允许控制学习图与我们的基线的距离:xyz空间上的k-NN。该框架在ModelNet 40上进行了测试,我们的网络生成的图形在总体准确性上超过基线0.3个点。

英文摘要:

Processing 3D pointclouds with Deep Learning methods is not an easy task. A common choice is to do so with Graph Neural Networks, but this framework involves the creation of edges between points, which are explicitly not related between them. Historically, naive and handcrafted methods like k Nearest Neighbors (k-NN) or query ball point over xyz features have been proposed, focusing more attention on improving the network than improving the graph. In this work, we propose a more principled way of creating a graph from a 3D pointcloud. Our method is based on performing k-NN over a transformation of the input 3D pointcloud. This transformation is done by an Multi-Later Perceptron (MLP) with learnable parameters that is optimized through backpropagation jointly with the rest of the network. We also introduce a regularization method based on stress minimization, which allows to control how distant is the learnt graph from our baseline: k-NN over xyz space. This framework is tested on ModelNet40, where graphs generated by our network outperformed the baseline by 0.3 points in overall accuracy.

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。

↑