Visualizing point cloud classifiers by curvature smoothing
Visualizing point cloud classifiers by curvature smoothing
复制标题
DOI：
--
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Ziwen Chen;Wenxuan Wu;Zhongang Qi;Fuxin Li
中科院分区：
文献类型：
--
作者：
Ziwen Chen;Wenxuan Wu;Zhongang Qi;Fuxin Li
最近，人们提出了几种直接在点云上运行的网络。理解它们对点云进行分类的机制具有重要的实用性，这可能有助于诊断这些网络并设计更好的架构。在本文中，我们提出了一种新的方法来可视化点云分类器的重要特征。我们的方法是基于平滑点云上的弯曲区域。在对突出特征进行平滑处理后，可以在网络上对得到的点云进行评估，以评估该特征对分类器是否重要。本文的一个技术贡献是提出了一种近似曲率平滑算法，该算法可以平滑地从原始点云过渡到等曲率点云，如均匀球。在平滑算法的基础上，我们提出了PCI-GOS （Point Cloud Integrated-Gradients Optimized Saliency，点云集成梯度优化显著性），这是一种可以自动找到覆盖形状最重要特征的最小显著性图的可视化技术。实验结果揭示了对不同点云分类器的见解。
Recently, several networks that operate directly on point clouds have been proposed. There is significant utility in understanding their mechanisms to classify point clouds, which can potentially help diagnosing these networks and designing better architectures. In this paper, we propose a novel approach to visualize features important to the point cloud classifiers. Our approach is based on smoothing curved areas on a point cloud. After prominent features were smoothed, the resulting point cloud can be evaluated on the network to assess whether the feature is important to the classifier. A technical contribution of the paper is an approximated curvature smoothing algorithm, which can smoothly transition from the original point cloud to one of constant curvature, such as a uniform sphere. Based on the smoothing algorithm, we propose PCI-GOS (Point Cloud Integrated-Gradients Optimized Saliency), a visualization technique that can automatically find the minimal saliency map that covers the most important features on a shape. Experiment results revealed insights into different point cloud classifiers.