Abstract
Graph-based methods have proven to be effective in capturing relationships among points for 3D point cloud analysis. However, these methods often suffer from suboptimal graph structures, particularly due to sparse connections at boundary points and noisy connections in junction areas. To address these challenges, we propose a novel method that integrates a graph smoothing module with an enhanced local geometry learning module. Specifically, we identify the limitations of conventional graph structures, particularly in handling boundary points and junction areas. In response, we introduce a graph smoothing module designed to optimize the graph structure and minimize the negative impact of unreliable sparse and noisy connections. Based on the optimized graph structure, we improve the feature extract function with local geometry information. These include shape features derived from adaptive geometric descriptors based on eigenvectors and distribution features obtained through cylindrical coordinate transformation. Experimental results on real-world datasets validate the effectiveness of our method in various point cloud learning tasks, i.e., classification, part segmentation, and semantic segmentation.
Abstract (translated)
基于图的方法已被证明在捕捉三维点云分析中各点之间的关系方面非常有效。然而，这些方法往往因为边界点连接稀疏和结点区域连接嘈杂而产生次优的图结构问题。为了解决这些问题，我们提出了一种新方法，该方法集成了图平滑模块与增强型局部几何学习模块。 具体而言，我们指出了传统图结构在处理边界点和结点区域方面的局限性，并提出了一个专门优化图结构、最小化不可靠稀疏和嘈杂连接负面影响的图平滑模块。基于这个优化后的图结构，我们将特征提取功能改进为包含本地几何信息的形式。这些包括通过自适应的基于特征向量的几何描述符获得的形状特征以及通过圆柱坐标变换得到的分布特征。 实验结果在现实世界数据集上验证了我们方法在各种点云学习任务（如分类、部件分割和语义分割）中的有效性。
URL
https://arxiv.org/abs/2601.11102
