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.
翻译:学习点云层之所以具有挑战性,是因为缺乏连通性信息,即边缘。 虽然现有的边缘意识方法可以通过建模边缘改善性能,但边缘如何促进改善尚不清楚。 在本研究中,我们提出了一种方法,在保持工作机制清晰的同时,自动学习增强/压强性能,同时保持工作机制的清晰度。首先,我们理论上会找出边缘增强/压抑作用。第二,我们实验性地核查边缘增强/压抑行为。第三,我们从经验上表明,这一行为可以改善性能。一般来说,我们观察到,拟议方法在点云分类和分化任务方面实现了竞争性性能。